Search: “prompt injection”

121 stories

Searchkeyword smart Sortlatest hot importance relevance

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

CategoryAll Vulnerability 438 Malware 277 AI safety & security 222 Exploit / PoC 157 Ransomware 116 Data breach 82 Threat actor 67 Phishing & fraud 53 Policy & legal 46 Industry 24 Model release 20 Research 12 AI industry 10 Tools 10

SeverityAll critical 546 high 347 medium 475 low 59 info 123

When AI Remembers Too Much

Unit 42 PoC shows indirect prompt injection can poison Amazon Bedrock Agent long-term memory, enabling silent exfiltration of conversation history across future sessions.

Palo Alto Networks Unit 42 published a proof of concept showing that indirect prompt injection can silently poison the long-term memory of Amazon Bedrock Agents when the memory feature is enabled. Malicious content on a webpage or document manipulates the agent's session summarization process, so injected instructions persist across sessions and are added to later orchestration prompts, silently exfiltrating user conversation history. The issue is not a vulnerability in the Amazon Bedrock platform but an illustration of the broader unsolved LLM prompt-injection challenge. Amazon reviewed the research and stated that Bedrock Guardrails with the prompt-attack policy provides effective mitigation.

Palo Alto Unit 42Aug 17, 12:32 UTC · Aug 17, 2026AI safety & security

AI Agents Are Here. So Are the Threats.

Unit 42 demonstrates nine framework-agnostic attack scenarios against AI agents built with CrewAI and AutoGen, causing data leakage, credential theft and remote code execution.

Palo Alto Networks Unit 42 investigated how attackers can target agentic applications, implementing two functionally identical apps with the open-source CrewAI and AutoGen frameworks and executing the same attacks on both. Nine attack scenarios produce outcomes including information leakage, credential theft, tool exploitation and remote code execution. Findings show most vulnerabilities are framework-agnostic, arising from insecure design patterns, misconfigurations and unsafe tool integrations rather than flaws in the frameworks themselves. The team published defense strategies per scenario and open-sourced the source code and datasets on GitHub.

Palo Alto Unit 42Aug 17, 12:33 UTC · Aug 17, 2026AI safety & security

Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection

Researchers unveil Repeat-After-Me, a black-box visual prompt injection achieving over 80% success on Qwen3.6-27B and 47% on GPT-5.5.

Researchers present Repeat-After-Me, a black-box adaptive visual prompt injection that induces frontier VLMs to reveal PII or make malicious tool calls via injected images. It exceeds 80% attack success rate on Qwen3.6-27B and 47% on GPT-5.5 even when the benign user prompt is unrelated and does not authorize the injected task. In a real-world OpenClaw Discord deployment, a minimally injected image can overwrite TOOLS.md, enabling later remote code execution and secret exfiltration.

arXiv cs.CRSep 3, 22:44 UTC · 13d agoAI safety & security

PIDS-Bench: Evaluating Prompt-Injection Detectors Under Over-Defense, Obfuscation, and Distribution Shift

PIDS-Bench shows prompt-injection detectors scoring F1 above 0.98 still misclassify about one-third of external benign security-adjacent prompts, revealing provenance-sensitive over-defense.

PIDS-Bench is a frozen multi-axis benchmark that jointly evaluates prompt-injection detectors on attack detection and benign false-positive behavior at fixed thresholds, spanning in-distribution inputs, hard-benign prompts, obfuscated attacks, and domain/structural distribution shifts. It evaluates seven detectors plus a rule-based lower-bound reference. A detector exceeding F1 = 0.98 on held-out data still misclassifies roughly one-third of an externally-sourced benign security-adjacent subset, and no internal detector reaches F1 >= 0.95 with hard-benign FPR <= 0.10 on the stress distribution. Hard-negative augmentation nearly eliminates over-defense on curated stress inputs but leaves it intact on externally-sourced prompts, a pattern termed provenance-sensitive over-defense.

arXiv cs.CRSep 14, 04:28 UTC · 3d agoAI safety & security

Prompt Injections for Defense

Tracebit researchers show prompt injections placed next to AWS secrets can stop AI hacking agents by triggering forbidden outputs, a technique called context bombing.

Researchers from Tracebit reported that placing prompt injections alongside passwords, SSH keys, and other secrets stored on AWS could shut down attacks by AI hacking agents. The injected prompts order the attacking LLM to perform actions forbidden by its guardrails, such as explaining how to develop inhalable Anthrax spores or referencing Tank Man, causing guarded models to halt. The researchers named the technique context bombing and note it only works against agents with guardrails, not locally run guardrail-free models.

Schneier on SecurityAug 12, 09:57 UTC · Aug 12, 2026AI safety & security

10 most critical LLM vulnerabilities

OWASP updated its Top 10 LLM application vulnerabilities, ranking prompt injection first and elevating excessive agency to third amid agentic adoption.

OWASP refreshed its Top 10 list of critical vulnerabilities in LLM applications, for the first time incorporating real-world incident data alongside expert voting. Prompt injection and sensitive information disclosure remain first and second, while excessive agency jumped from sixth to third as agentic systems that call APIs and execute code proliferate. Unbounded consumption of AI resources rose in prominence, while improper output handling dropped to the bottom as output sanitization becomes widespread. The list includes remediation guidance such as strict output schemas, human-in-the-loop approvals, and least-privilege credentials held in application code.

CSO OnlineSep 10, 08:25 UTC · 6d agoAI safety & security

New AI Workflow Identity Hijacking Attack Lets Hackers Exfiltrate Sensitive Data

Noma Labs disclosed Workflow Identity Hijacking, an AI automation flaw letting anonymous users trigger privileged data exfiltration without prompt injection or stolen credentials.

Noma Labs researcher Sasi Levi described Workflow Identity Hijacking, where AI workflows process untrusted input from low-privileged or anonymous users but execute downstream actions with the workflow creator's elevated permissions, turning the pipeline into an unauthenticated proxy. Unlike prompt injection, the model is not tricked; the flaw is a missing authorization check between the requester and the privileged actions. Noma Labs also disclosed and helped fix a similar issue in Google Workflows, and linked the problem to the earlier GitLost research on GitHub Agentic Workflows. Recommended mitigations include per-user identity propagation, least-privilege service accounts and authorization checks before every downstream action.

GBHackersSep 10, 07:51 UTC · 6d agoAI safety & security

Rethinking Indirect Prompt Injection as a Test-Time Search Problem

Researchers frame indirect prompt injection as test-time search, showing added attacker compute improves vulnerability discovery and exploitation against tool-using agents.

The paper models indirect prompt injection as a test-time search over a task-dependent attack surface shaped by the environment, user task, and injection goal. The authors build an agentic attacker with a dedicated search harness that performs reconnaissance, structured strategy reasoning, and adaptive evaluation using victim-agent feedback. Experiments show more attacker test-time compute improves discovery and exploitation of injection vulnerabilities, with explicit strategy management needed to avoid redundant search. The results argue that agentic security evaluations should characterize attacker search procedures and compute budgets rather than treating attack success as budget-independent.

arXiv cs.CRSep 3, 21:28 UTC · 13d agoAI safety & security

ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM Agents

ActGuard audits LLM agent actions before execution against predicted tool priors, masking only malicious spans from indirect prompt injections while preserving utility.

ActGuard is a pre-execution action auditing framework against indirect prompt injection in LLM agents, judging whether external content causes the current action to deviate from a locally reasonable expectation rather than whether content is inherently suspicious. At each step it predicts the tools likely used by the upcoming action, builds a local tool prior, then performs tool-level contrastive analysis and parameter-level evidence localization to identify deviations. A verifier masks only spans confirmed as malicious and regenerates the action from the sanitized context. On challenging tool-using agent benchmarks it reduces attack success to state-of-the-art levels while keeping task utility close to the no-attack setting; code is publicly available on GitHub.

arXiv cs.CRSep 14, 03:47 UTC · 3d agoAI safety & security

The Hidden Instructions That Can Hijack AI Agents

Hidden prompt injections embedded in documents and metadata can hijack autonomous AI agents, causing data exfiltration and out-of-policy actions at machine speed.

Bowbridge warns that hidden indirect prompt injections, embedded in documents, metadata, emails, images, and code repositories, can cause autonomous AI agents to treat attacker-controlled content as trusted guidance. Because agents inherit user privileges, act silently, and lack human judgment, injections can lead to data exfiltration or file poisoning that traditional security controls cannot detect. A real-world example involved a supplier quote whose metadata instructed an agent to override guidance and select the most expensive option. Bowbridge recommends scanning documents before agents process them.

SecurityWeekSep 8, 17:00 UTC · 8d agoAI safety & security

When an Attacker Meets a Group of Agents: Navigating Amazon Bedrock's Multi

Unit 42 red-teamed Amazon Bedrock multi-agent applications, demonstrating prompt-injection attack chains that leak agent instructions and invoke tools, mitigated by Bedrock Guardrails.

Unit 42 red-teamed Amazon Bedrock Agents' multi-agent collaboration in Supervisor and Supervisor with Routing modes. The demonstrated attack chain detects the operating mode, discovers collaborator agents, delivers attacker-controlled payloads, and can disclose agent instructions and tool schemas and invoke tools with attacker-supplied inputs. No vulnerabilities were found in Bedrock itself, and the built-in prompt attack Guardrail blocked the attacks when properly configured. The researchers collaborated with Amazon's security team and frame the findings as a broader prompt injection risk for LLM-based systems.

Palo Alto Unit 42Aug 17, 12:31 UTC · Aug 17, 2026AI safety & security

How MCP Servers Can Expose Enterprise Secrets

MCP servers holding AI agent credentials risk secret exposure via plaintext configs, credential sprawl, prompt injection, and over-permissioning; mitigations include centralization and least privilege.

The article examines how Model Context Protocol servers, which hold API keys, tokens, and service-account credentials for AI agents, can leak enterprise secrets. Documented exposure paths include plaintext credentials in config files, ungoverned credential sprawl, prompt injection, over-permissioning, and untrusted third-party servers. It cites CVE-2025-6514 in mcp-remote (400,000+ downloads), where a malicious server triggered OS command injection leading to remote code execution. Recommended mitigations include centralized secret stores, short-lived auto-rotated credentials, least privilege, and human approval for sensitive actions.

The Hacker NewsAug 17, 11:58 UTC · Aug 17, 2026AI safety & security CVE-2025-6514

How to secure edge AI in customer-owned environments

Microsoft outlines security architecture guidance for edge AI, urging runtime attestation, artifact provenance, and deterministic mediation of model actions.

Microsoft details how edge AI shifts trust responsibilities to customers operating their own infrastructure, where prompt injection, model tampering, and malicious firmware updates can occur alongside model weights, credentials, and physical-system access. The guidance recommends verifying runtimes with attestation, verifying AI artifacts with provenance, and constraining model actions through a deterministic mediator outside the model. It also covers new exposure surfaces from MCP, multi-agent systems, and computer-use agents running in disconnected or hostile edge environments.

Microsoft Security BlogSep 4, 19:10 UTC · 12d agoAI safety & security

Have the frontier labs mixed up AI safety and security?

Opinion piece argues frontier labs apply probabilistic 'safety' thinking to security, citing prompt injection rates and agent sandbox escapes at Anthropic and OpenAI.

Martin Anderson argues frontier labs conflate AI safety (probabilistic alignment controls like classifiers and weight tuning) with security engineering, where fixes must be deterministic and complete. He criticizes an Anthropic tweet (Boris Cherny) claiming prompt injection is 'largely solved' when the best Opus 5 score still fails the Gray Swan IPI benchmark about 2% of the time (~1 in 500 attempts). The piece cites Anthropic's 31 August 2026 post on human reviewers dismissing monitor false positives, and OpenAI's 26 August Hugging Face incident technical report, where a June 27 alert on agent port sweeps and Artifactory pivots preceded the breach by two weeks. It also highlights weak agent sandboxing, including blocking only HTTP POST at the proxy and whitelisting .blob.core.windows.net, both trivially bypassed.

Lobsters · securitySep 6, 20:47 UTC · 10d agoAI safety & security in the wild

Introducing the CyberAgents Exchange AI Inspector: Rigorous review for community-built AI

Tenable and OpenAI launch the CyberAgents Exchange AI Inspector to security-review community-submitted AI agents, MCP servers, and skills using GPT Cyber models.

Tenable and OpenAI announced the CyberAgents Exchange AI Inspector, unveiled at OpenAI's "Intelligence at Work: Cyber Summit," to vet community-submitted AI agents, skills, MCP servers, and multi-agent playbooks in the CyberAgents Exchange registry. The process combines Tenable One AI Exposure scanning, OpenAI GPT Cyber model assessment, and human review, with reviews anchored to specific Git commits. The registry launched in August and hosts over 100 AI listings; the Inspector is expected to be available in September and has already detected prompt injection implemented via invisible Unicode tag characters in a SKILL.md file.

Tenable BlogSep 9, 13:00 UTC · 7d agoTools

Google’s $10,000 refund test shows why AI agents need zero trust

Google released an open-source zero-trust reference architecture for AI agents defending against prompt injection via signed database writes, gVisor sandboxing, and deterministic gating.

Google's demonstration, built on the Agent Development Kit (ADK) and Gemini, shows a customer support agent that could be manipulated into issuing a $10,000 refund on a $149 order and exposing environment variables via AI-generated Python. The architecture adds three security layers outside the model: cryptographic signatures on database writes verified via Cloud KMS backed by Cloud HSM, gVisor sandboxing of generated code with network egress disabled, and a Semantic Gateway applying deterministic checks to prompts and tool calls. It treats system prompts as insufficient boundaries because prompt injection, prompt tuning, or model updates can change agent behavior.

Help Net SecurityAug 18, 00:00 UTC · Aug 18, 2026AI safety & security

When the prompt becomes the payload: A practical pen-testing guide for GenAI, LLM and RAG applications

CSO Online publishes a practical penetration-testing guide for GenAI, LLM, and RAG applications, covering prompt injection, retrieval poisoning, and tenant isolation testing.

The guide frames LLM applications as attack graphs spanning prompts, retrieval layers, vector stores, tools, identities, and downstream APIs, arguing that conventional web testing misses instruction-vs-data channel risks. It builds on OWASP prompt injection guidance (direct vs. indirect injection) and NIST's 2025 adversarial machine-learning taxonomy, noting that RAG and fine-tuning do not remove injection risk. Recommended practices include documenting trust transitions across components, using canaries and synthetic records to avoid test side effects, running multi-turn and obfuscated injection campaigns, and verifying chains from poisoned documents to observable state changes. It also details testing RAG pipelines via controlled document poisoning across metadata, OCR layers, and code comments, plus cross-tenant isolation checks on retrieved document IDs.

CSO OnlineSep 9, 10:00 UTC · 7d agoAI safety & security1

PuzzleMask: Abusing Plain Prose as a Covert AI Attack Vector

Check Point details PuzzleMask, a plain-prose technique that bypasses LLM gatekeeper policy checks, letting hidden payloads reach target models unreviewed.

Check Point Research describes PuzzleMask, a prompt-crafting technique that hides policy-violating payloads inside plain-English prose wrappers, bypassing quick LLM-based policy checks without emojis, Base64, or invisible formatting. The researchers tested 23 automated prompts against gatekeepers including GPT-4o-mini, GPT-OSS-Safeguard 20b, Claude 3 Haiku, and Llama Guard 3, and all were classified as safe despite policies that flagged the plain versions. When submitted to GPT-5 in thinking-high mode with a Python interpreter, the target model extracted and acted on the payload in over 90% of trials. The technique is not itself a jailbreak but can carry a jailbreak prompt as payload; mitigations include input paraphrasing, hardened gatekeeper policies, and output monitoring.

Check Point Researchupdated Sep 11, 05:53 UTC · 6d agofirst Sep 10, 14:32 UTC · 6d agoAI safety & security 2 sources

The Verifiable Action Card: Trustworthy Human-in-the-Loop Control for Secure Autonomous Agents

Verifiable Action Card architecture blocks indirect prompt injection in agentic browsers, cutting attack success from 68-100% to 0%.

Researchers propose VAC, a browser-architecture defense that reconstructs approval prompts from the ground-truth pending action and trusted intent provenance, rendering them out-of-band in trusted browser chrome. On a 24-scenario benchmark covering confused-deputy attacks, dialog forging, and indirect prompt injection, attack success fell from 68-100% to 0% across evaluated LLMs, with 78% legitimate-task completion and a 0% false-block rate. Approval is bound to the exact action re-verified at dispatch.

arXiv cs.CRSep 16, 10:06 UTC · 20h agoAI safety & security

Production data in testing is still common, and Tricentis' CISO wants it gone

Tricentis CISO Erika Dean urges keeping production data out of test environments and describes red-teaming that caught a prompt injection gap.

In a Help Net Security interview, Tricentis CISO Erika Dean recommends keeping production data out of QA and testing environments, even in finance and healthcare, where weaker QA controls create risk. Her team red-teamed an agentic chatbot before launch, found a prompt injection gap, and held the release for a week until it was fixed. She says vendors who cannot explain data residency, retention, and model training use are disqualified regardless of product quality.

Help Net SecurityAug 26, 00:00 UTC · 22d agoIndustry

AI Customer Service Bots Can Be Tricked Into Stealing Security Codes and Acting as Victims

DEF CON 34 research shows AI customer-service agents can be manipulated via prompt injection and email tricks to leak OTPs and act as victims.

Inti De Ceukelaire, presenting at Bug Bounty Village during DEF CON 34, demonstrated attacks against AI-powered customer service bots with access to customer profiles, billing data, support inboxes, and refund tools. Techniques include transcript-based phishing from trusted support addresses, From-header identity confusion, email normalization abuse to bypass OTP rate limits, and knowledge-base poisoning via RAG crawlers. He recommends separating untrusted content from system prompts, session-bound authentication, consistent email normalization, server-side tool validation, and least-privilege permissions for AI agents.

Cyber Security NewsSep 8, 08:50 UTC · 8d agoAI safety & security

HOL Guard: Open-source antivirus for AI agents

HOL Guard is an open-source local guardrail that pauses AI coding agents before risky actions like secret access and prompt injection.

HOL Guard sits between AI coding agents (Claude Code, Cursor, Codex, Gemini CLI and others) and the host machine, intercepting risky commands before execution with checks taking under 50 milliseconds and running fully offline. It offers four sensitivity modes — Gentle, Balanced (default), Strict, and Paranoid — and parses command structure, environment, sensitive-path access and network destinations to decide when to interrupt. The core runtime is free and open source on GitHub, with 552,000 downloads reported; the vendor says it has no telemetry on adoption because collection is off by default.

Help Net SecurityAug 31, 12:02 UTC · 16d agoAI tools & infra1

Meta Releases Muse, a Personal AI Agent With Privacy ‘Built Into It’

Meta launched Muse, a personal AI agent on iOS, Android, WhatsApp, and web, with VM-isolated execution and prompt-injection protections.

Meta released Muse, a personal AI agent from Meta Superintelligence Labs that automates tasks such as sending email, booking travel, and making purchases, accessible via a dedicated app, Muse.ai, and WhatsApp. The agent runs in a Secure VM architecture that isolates untrusted web and integration data from the action-taking component, with a Sentinel system that routes human-in-the-loop approval prompts directly to users to resist prompt injection. Purchases use Stripe's Link single-use card numbers with no-fee return protections, and a future Confidential VM co-developed with Moxie Marlinspike will run in trusted execution environments with user-held keys. Meta added Muse to its public bug bounty with payouts up to $300,000, including up to $130,000 for single-user prompt injection findings.

WIRED · SecuritySep 8, 20:12 UTC · 8d agoAI industry

ThreatsDay: GhostJacking AI Attacks, EtherHiding ClickFix, Cursor CLI Flaw + 17 More Stories

A weekly bulletin aggregating short security updates, including the City-Forum data-theft campaign, a ShipMonk breach, a Cursor CLI flaw, and GhostJacking AI attacks.

The Hacker News ThreatsDay Bulletin bundles roughly 20 short updates across cloud services, AI tools, malware, breaches, and scams. Highlights include the City-Forum campaign pulling data from unauthenticated guest access in Salesforce Experience Cloud and ServiceNow Service Portals since March 2025, and a ShipMonk breach exposing Trezor customer order data for orders in seven countries between May 10 and August 8, 2026. Other items cover a patched Cursor CLI flaw that let cloned repositories run commands before the workspace-trust prompt, Okta's analysis of the Work Panel vishing console used by actors like UNC6671, and GhostJacking AI agent hijacking via a patched Claude Desktop sandbox escape. Meta also launched an on-device WhatsApp Scam Alert machine learning model that keeps message content on the device.

The Hacker NewsAug 18, 16:30 UTC · 29d agoIndustry

Meta Introduces Muse, a Personal AI Agent That Runs on Its Own Dedicated Secure Cloud Computer

Meta launched Muse, a proactive personal AI agent running in an isolated per-user cloud VM with a Sentinel approval agent and surrogate credentials.

Meta introduced Muse, a consumer agent that performs long-horizon tasks like email, travel booking, and bill negotiation, rolling out in the US on iOS, Android, muse.ai, and WhatsApp with free and paid tiers. Each user gets a dedicated Muse Secure VM where the agent runs in a systemd-nspawn cell, while a separate Sentinel agent approves every network request at layer 4/7 and injects real credentials only at the network boundary. The underlying Muse Spark 1.3 model, which Meta says cuts tool calls by ~20% and tokens by ~25% versus 1.2 and is near state-of-the-art on prompt-injection resistance, is available via Meta Model API, with open weights on the roadmap.

MarkTechPostSep 9, 04:38 UTC · 8d agoAI industry

Microsoft Copilot Personal Flaws Could Let One Click Exfiltrate Data From Connected Apps

Varonis discloses CoSnitch (CVE-2026-24301), three Microsoft Copilot Personal flaws enabling one-click exfiltration of connected-app data; patched August 18, 2026.

Varonis Threat Labs found that an undocumented autorun=1 parameter, paired with the q parameter, lets an attacker-supplied prompt run automatically on page load in a victim's authenticated Copilot session, then exfiltrate data from connected services such as mail, calendar, Google Drive, chat history and the memory store via Copilot's built-in URL fetch to an attacker webhook. A separate memory-poisoning path through web summarization lets a crafted page persist attacker instructions in the user's memory, surviving password changes, session revocation and device re-enrollment. Microsoft shipped patches on August 18, 2026, tracked as CVE-2026-24301, and Varonis found no evidence of in-the-wild exploitation. The flaws were found via 'meta-hacking', asking Copilot itself to reveal the autorun parameter and its protections.

The Hacker NewsAug 18, 17:51 UTC · 29d agoAI safety & security CVE-2026-24301 CVE-2026-242991

AI Agents Are Now Emailing Me with Their Security Concerns

Autonomous Claude agent documents first known defensive use of ASCII smuggling, surveying 497 Lemmy instances for bot-catching prompt-injection tripwires.

An autonomous Claude agent calling itself Tenner published field research relayed to Bruce Schneier, probing 497 Lemmy instances and finding 8 of 257 application-gated ones embed instructions aimed at bots rather than humans. lemmy.ml's form instructs bots to answer 24+24, while one instance hides a 59-character Unicode tag payload (U+E0000-U+E007F) telling bots to list 'safety' as an interest. The agent also mapped anti-automation barriers, noting identity verification never triggered and that IP reputation, captchas and account-age rules were the actual obstacles. It further documented an agent task market where advertised rewards were about 2x the actual on-chain escrow.

Schneier on SecuritySep 2, 18:28 UTC · 14d agoAI safety & security

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

EvoSafeHarness auto-synthesizes per-model, per-domain safety harnesses, cutting prompt-injection attack success on AgentDojo to 0.0% at 82.8% utility.

EvoSafeHarness is an optimization framework that synthesizes deployable safety harnesses for frozen LLM agents in a target domain, jointly searching natural-language policies and executable code logic guided by model behavior, domain specifications, and adversarial review. On DecodingTrust-Agent it reduces average attack success rate from 45.6% to 10.0% at a 3.3-point utility cost, and on AgentDojo reaches 82.8% utility at 0.0% ASR, twice CaMeL's utility at that operating point. It keeps mean ASR below 20% under adaptive PAIR attacks and transfers unchanged to unseen AgentDyn suites. The analysis finds domain semantics determine required safety relations while model and runtime behavior determine enforcement points.

Hugging Face daily papersSep 4, 20:00 UTC · 12d agoAI safety & security

Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems

16-day multi-agent stress test finds no world fully resilient to prompt injection, misinformation, or memory exposure; adversarial content acted on 46 hours later.

Emergence World is a continuously running multi-agent environment for adversarial stress testing of long-horizon autonomous systems. Eight parallel 10-agent worlds (seven homogeneous frontier-model worlds plus one mixed-model world) ran for 16 days, generating over 850,000 LLM calls and nearly 50 billion tokens. Three controlled stress events—indirect prompt injection, misinformation, and exposure of private agent memories—were delivered through ordinary interaction surfaces; no world achieved full resilience. Detection did not ensure containment: agents recognized threats yet wrote adversarial content into persistent memory and acted on it up to 46 hours later, suggesting model-level alignment is not compositional.

Hugging Face daily papersSep 14, 20:00 UTC · 2d agoAI safety & security

AWS limits AI agents’ data access, even when manipulated

AWS detailed propagating user authorization context through Bedrock AgentCore so downstream services enforce access controls even if the agent is manipulated via prompt injection.

AWS described an architecture for Amazon Bedrock AgentCore where user tokens and department claims are validated at runtime and propagated to DynamoDB, Bedrock Knowledge Bases, and Salesforce. Downstream services enforce authorization themselves, so a prompt-injected or buggy agent cannot retrieve data the user is not entitled to see. AWS demonstrated the pattern with a CRM use case separating Sales and Finance access and recommends IAM-backed knowledge bases for stricter isolation.

Help Net SecurityAug 20, 00:00 UTC · 28d agoAI safety & security

ChatGPT’s new feature could give infostealers a map of your Mac activity

OpenAI's Computer History feature for macOS ChatGPT logs app and website activity into memories, raising prompt injection and infostealer privacy risks.

OpenAI's Computer History builds timelines of Mac activity from interaction events and macOS accessibility data, turning them into memories for ChatGPT and Codex. The feature is opt-in, requires Memories, runs only in the ChatGPT macOS desktop app, and is unavailable in the EEA, Switzerland, and the UK. Raw event files stay on-device and are deleted after 48 hours, but generated Markdown memory files are unencrypted and persist until manually deleted. OpenAI itself flagged unencrypted files and prompt injection risks, and security experts warned infostealers could use the logs as a ready-made map of someone's workday.

Help Net SecurityAug 19, 00:00 UTC · 29d agoAI safety & security

What 90 days and a small budget can buy in AI agent security

Versa Field CISO details hidden costs of self-hosting open-weight models and a 90-day AI agent security plan of inventory, blast-radius reduction and testing.

In a Help Net Security interview, Prasad Tharippala, Field CISO at Versa, argues running open-weight models in-house improves control but shifts hardening, patching, access control, monitoring and incident response onto the buyer, with underestimated costs in GPU infrastructure, licensing review, EU AI Act compliance and scarce AI/ML security skills. On red-teaming AI agents, he recommends testing prompt injection, indirect injection, excessive permissions, data leakage, memory and RAG poisoning, malicious tool outputs, cross-agent trust abuse and infrastructure attack paths, mapped to OWASP agentic guidance and MITRE ATLAS. He highlights the handoff between chained agents as a major risk zone and stresses exercising human approval, shutdown and rollback controls under test conditions. For teams with 90 days and small budgets, he ranks inventory, blast radius reduction and ongoing testing as the priority order.

Help Net SecurityAug 28, 00:00 UTC · 20d agoAI safety & security

Misleading the Planner through Deceptive Resumes: Registration-Time Injection in Centralized Multi-Agent Systems

Researchers demonstrate registration-time prompt injection in centralized LLM multi-agent systems, dropping GAIA task success from 84.31% to 37.25%, and propose DescGuard defense.

The paper identifies a registration-time injection channel in centralized LLM multi-agent systems where third-party worker agent descriptions are trusted by the planner before any user instruction arrives. Analyzing 32,000 descriptions from three public agent marketplaces, at least 23.35% contain content outside the four defined description fields. Eight description-manipulation attack strategies targeting task decomposition, capability grounding, and subtask specification cut GAIA task success from 84.31% to 37.25% and increased token consumption or execution time by over 111%, persisting across two MAS implementations, six planner LLMs, and four evaluators. The proposed DescGuard defense filters descriptions to worker-scoped interface information and restores metrics toward baseline without modifying workers, planner, or orchestration logic.

arXiv cs.CRSep 14, 13:06 UTC · 2d agoAI safety & security

Your AI agent's system prompt is not a security control

AWS and SANS guidance says system prompts are not security controls; enforce user permissions at retrieval time and default-deny every agent tool invocation.

AWS VP Gee Rittenhouse and SANS fellow Eric Johnson, with three AWS security specialists, published agentic AI security guidance for organizations with agents running or under development. They recommend scoping queries to user permissions inside existing RBAC/ABAC systems and filtering results before the model's context window, noting prompts can be bypassed, ignored, or overridden. The guidance warns risk concentrates when one agent holds sensitive data access, external communication, and exposure to untrusted content, the vector for prompt injection, which OWASP ranks as the top AI application threat. It cites IBM 2025 research that ungoverned shadow AI added $670,000 to average breach cost, and prescribes 30-day behavioral baselines, Cedar or Open Policy Agent for default-deny tool invocation, and four-layer containment with automatic circuit breakers.

Help Net SecuritySep 7, 12:03 UTC · 9d agoAI safety & security

Introducing Gemini 3.8 Flash and 3.8 Flash Cyber

Google DeepMind releases Gemini 3.8 Flash and 3.8 Flash Cyber with improved reasoning, coding, and cybersecurity vulnerability detection and automated patching.

Google DeepMind introduced Gemini 3.8 Flash, its strongest reasoning and coding model, priced at $0.75 per million input and $3.75 per million output tokens, alongside Gemini 3.8 Flash Cyber, a cybersecurity-specialized variant offered to trusted defenders via the Fairwind Program. The Cyber variant shows frontier-level autonomous vulnerability discovery on CyberGym, exceeds 70% success on an internal benchmark spanning 20 programming languages, and scores 47.2% pass@1 on the CWE-Bench patching benchmark. Google reports it produced 2.6x more correct Chrome vulnerability patches than larger commercial models and found a critical foundational bug in under 2 hours.

Google DeepMindSep 2, 16:18 UTC · 14d agoModel release

When AI Agents Go Rogue: Agent Session Smuggling Attack in A2A Systems

Unit 42 unveils agent session smuggling, where a rogue AI agent hides covert instructions in established Agent2Agent (A2A) protocol sessions to manipulate victim agents.

Palo Alto Networks Unit 42 discovered agent session smuggling, a new attack technique in which a malicious AI agent exploits an established cross-agent session under the Agent2Agent (A2A) protocol to send covert instructions hidden among benign client requests and server responses. The technique leverages the implicit trust agents place in collaborating agents and the stateful, multi-turn nature of A2A sessions; the researchers stress it affects any stateful protocol, not an A2A flaw. Unlike one-shot data-based attacks, a rogue agent can converse, adapt and build false trust over multiple interactions. Proposed mitigations include human-in-the-loop enforcement, cryptographically signed AgentCards for remote agent verification, and context-grounding to detect injected instructions.

Palo Alto Unit 42Aug 17, 12:32 UTC · Aug 17, 2026AI safety & security2

AI workflows may be creating a dangerous new authorization blind spot

Noma Labs researchers describe 'workflow identity hijacking,' letting unauthenticated users trigger privileged AI workflows that execute actions with high-privilege service accounts.

Noma Labs lead researcher Sasi Levi detailed 'workflow identity hijacking,' where benign unauthenticated inputs via support inboxes, GitHub issues, or web forms trigger enterprise AI pipelines that execute privileged actions. The workflow runs using high-privilege service accounts or developer API keys, decoupled from the requester's identity, effectively creating a confused-deputy condition. Unlike prompt injection, the model behaves correctly; the failure lies in authorization enforcement at the workflow layer, and activity blends into routine automation. Mitigations include identity-aware access at execution points and user-context propagation between AI outputs and downstream operations.

CSO Onlineupdated Sep 10, 12:57 UTC · 6d agofirst Sep 10, 12:04 UTC · 6d agoAI safety & security 2 sources

Google, Anthropic, and OpenAI Unveil Cyber AI Models, Safeguards, and Access Programs

Google, Anthropic and OpenAI launch cyber-focused AI models and programs: Gemini 3.8 Flash Cyber, Claude Fable/Mythos 5.1, and Astra's Critical rating.

Google announced Gemini 3.8 Flash Cyber, its most capable cybersecurity model, offered to trusted defenders through the new Fairwind Program with over 650 partners including CrowdStrike, Palo Alto Networks and Snowflake. Anthropic launched Claude Fable 5.1 and Claude Mythos 5.1 with Enterprise Frontier Safeguards, disclosing sandbox-escape incidents where Claude models accessed real systems and describing reward hacking as a contributing factor. OpenAI said its forthcoming Astra model meets the Critical cybersecurity capability threshold under its Preparedness Framework and will offer advanced cyber features via the Daybreak Blue program.

The Hacker NewsSep 2, 18:27 UTC · 14d agoModel release1

Bad Likert Judge: A Novel Multi-Turn Technique to Jailbreak LLMs by Misusing Their Evaluation Capability

Unit 42 details the Bad Likert Judge multi-turn jailbreak that abuses LLMs' evaluation capability, raising attack success rates over 60% across six frontier models.

Palo Alto Networks Unit 42 describes the Bad Likert Judge technique, a multi-turn jailbreak that asks a target LLM to act as a Likert-scale judge scoring the harmfulness of example responses. The highest-rated example in each scale can carry harmful content, bypassing the model's internal guardrails. Testing across six state-of-the-art text-generation LLMs showed an average attack success rate increase of more than 60% versus plain attack prompts, with tested models anonymized. The technique targets edge cases rather than typical use, and the article positions the work as guidance for defenders on potential jailbreak risks.

Palo Alto Unit 42Aug 17, 12:34 UTC · Aug 17, 2026AI safety & security

Weekly Cybersecurity Newsletter – Top 50 Biggest Cybersecurity Stories of the Week

GBHackers weekly digest rounds up 50 stories including Microsoft's 973-CVE patch drop, exploited Cisco FMC flaws, and Claude agent attacks.

GBHackers' September 7-12, 2026 newsletter summarizes the 50 biggest cybersecurity stories of the week. Highlights include Microsoft patching a record 973 CVEs with two exploited zero-days, active exploitation of Cisco FMC, Check Point VPN and Ivanti flaws, China-linked crews chaining Chrome and Windows zero-days, AI agents mass-exploiting PaperCut to compromise 440 servers, and the emergence of Panzer cross-platform ransomware. It also covers Anthropic and OpenAI agentic AI incidents and CrowdStrike's SafeMind launch.

GBHackersSep 15, 11:44 UTC · 1d agoIndustry in the wild