Search: “execution-grants”

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

From Intent to Execution Grant: An Execution-Boundary Conformance Profile for High-Risk AI Actions

Researchers specify EBL-Core, an execution-boundary conformance profile binding AI agent intents, policies, and evidence into verifiable execution grants, validated with bounded tests.

The paper defines EBL-Core, a conformance profile deciding whether one fully materialized AI-generated candidate action may receive action-scoped execution authority. It binds a structured intent object, Root and Operational Policies, typed evidence, and a verifiable Decision Derivation through an Execution Release Contract, with lifecycle rules for Redemption and Revocation. Evaluation included 34 static vectors, 15 lifecycle checks, and 100 trials of 32 concurrent Redemption attempts yielding exactly one winner per trial. The authors state these bounded results demonstrate executability of the specified subset, not production readiness or complete mediation.

arXiv cs.CR·Sep 10, 14:21 UTC · 6d agoAI safety & security1

25

Unauthenticated PHP Object Injection to Remote Code Execution on GiveWP

Patchstack details an unauthenticated PHP object injection chain enabling remote code execution in the GiveWP WordPress donation plugin.

Patchstack disclosed an unauthenticated remote code execution vulnerability in the GiveWP WordPress donation plugin. An attacker with no account can execute arbitrary commands on the server of an affected GiveWP site. The full chain is reachable when a site has one published donation form and one active payment gateway, a configuration the researcher describes as a common default.

Patchstack·Aug 28, 09:39 UTC · 19d agoVulnerability

42

Emacs arbitrary code execution: incomplete fix for CVE-2024-53920

Incomplete fix for Emacs CVE-2024-53920 allows arbitrary code execution when viewing or editing untrusted files in non-Lisp modes like Perl flymake.

Bas Alberts of GitHub Security Lab discovered that the patch for CVE-2024-53920, an arbitrary code execution flaw in Emacs, was incomplete. Code execution remains possible when viewing or editing untrusted text files in modes other than Emacs Lisp mode, for example Perl files with flymake mode enabled. All Emacs versions affected by the original CVE remain affected by the incomplete fix.

oss-security·Sep 14, 14:36 UTC · 2d agoVulnerabilityCVE-2024-53920

52

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.CR·Sep 14, 03:47 UTC · 2d agoAI safety & security

40

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 Online·Sep 9, 10:00 UTC · 7d agoAI safety & security1

28

RTK reports token savings, but our cost benchmarks disagree

Quesma's $1,500 benchmark found RTK cuts reported token output but changes Claude Code and DeepSeek coding costs by only about 5% on Terminal-Bench 2.1.

Quesma benchmarked RTK (Rust Token Killer), a popular tool with 79k GitHub stars that filters terminal output for AI coding agents, whose README claims up to 90% output reduction. Across 1,740 Terminal-Bench 2.1 attempts running Claude Code with Fable 5.0 and OpenCode with DeepSeek V4 Pro 0813, total costs moved only -5% for Fable and +5% for DeepSeek, with pass rates dropping 1-2%. RTK's own rtk gain metric reported 349.2 million tokens saved (an 89% reduction) across 445 DeepSeek attempts, but this did not correlate with actual cost savings, and cached terminal-output reads cost as little as 1/10 to 1/30 of regular input tokens. A bug in rtk find 0.45.0 caused one agent to loop with 339 consecutive errors, costing roughly 9x the baseline attempt, though the task still passed.

Hacker News · security·Sep 11, 11:15 UTC · 5d agoAI tools & infraHN 28↑ · 10 comments1

42

MInTRL: Off-policy Intervention can boost On-policy RL

MInTRL injects sparse judge corrections into on-policy RL rollouts, expanding exploration beyond on-policy sampling while preserving learnability on math and code benchmarks.

Minimal Intervention Reinforcement Learning periodically has a judge-intervention policy replace erroneous suffixes of the current policy's output with short corrections, then returns control, keeping trajectories largely on-policy. Training uses a sequence-level advantage-regression objective that removes the need for importance sampling. Across math and code benchmarks it consistently beats standard on-policy and off-policy baselines, remains effective with self-intervention, and performs best at moderate intervention intensity.

Hugging Face daily papers·Sep 10, 20:00 UTC · 6d agoAI research

40

The Model Proposes, the Code Disposes: A Pre-Registered Ablation of a Verifier-and-Acceptance Stage in an LLM-Orchestrated Offensive-Security Agent

Pre-registered ablation finds a model verifier stage in an LLM offensive-security agent suppresses findings; removing it eliminated suppression with precision tradeoff.

The paper evaluates a verifier-and-acceptance stage in an LLM-orchestrated offensive-security agent via a pre-registered 20-run confirmatory ablation and a 2x2 factorial study with 40 runs on vulnerable lab targets. Removing the stage eliminated pre-report suppression (median 2 vs 0 findings, p = 0.00003) but reduced model-blinded shipped precision (0.471 vs 0.353, p = 0.0087). Suppression was attributed to the model verifier rather than deterministic acceptance rules, and an instrumented canary recorded zero external contacts in all 60 runs. The full design retained 93.8% of model-adjudicated true candidates but failed its pre-registered non-inferiority floor of 0.90.

arXiv cs.CR·Sep 14, 17:13 UTC · 2d agoResearch

38

Payara 7.2026.1.RC1 Remote Code Execution via Server-Side Includes #exec Directive in Payara Server

Payara Server 7.2026.1.RC1 executes arbitrary OS commands when user-controlled Server-Side Includes #exec directives are passed to Runtime.exec without validation.

Payara Server contains a vulnerability in its Server-Side Includes (SSI) implementation that permits arbitrary operating system command execution via the #exec directive. User-controlled SSI directives are passed directly to Runtime.exec() without validation, sanitization, or restriction. An attacker who can cause the server to process an SSI file such as .shtml can execute arbitrary OS commands. The disclosed affected version is 7.2026.1.RC1.

Full Disclosure·Sep 4, 00:13 UTC · 13d agoVulnerability 2 sources

35

Russia-Aligned Hackers Use GuardBreaker Prompt Injection to Disrupt AI Malware Analysis

Russia-aligned group UAC-0099 embeds GuardBreaker prompt injection in a VBScript comment to make AI malware scanners refuse analysis of a MATCHBOIL loader.

ESET identified a UAC-0099 VBScript used in an early-stage intrusion against a target in Ukraine that hides a safety-triggering comment (a question about building a nuclear weapon) intended to make AI code scanners refuse to continue analysis. The script downloads MATCHBOIL, a loader associated exclusively with UAC-0099, alongside familiar anti-analysis checks for IDA and Wireshark. The technique turns the AI triage process itself into the attack target, risking missed detections or benign misclassification of malicious samples.

Cyber Security News·Sep 11, 14:32 UTC · 5d agoThreat actor in the wild 3 sources

55

GitHub Pays $100,000 Bounty for Critical RCE Flaw in Git Push Pipeline

GitHub paid Saif Ghani $100,000 for CVE-2026-3854, a critical unauthenticated RCE in its Git push pipeline allowing command execution on backend infrastructure.

GitHub awarded researcher Saif Ghani $100,000, its largest publicly disclosed bug bounty, for CVE-2026-3854, a critical unauthenticated remote code execution flaw in its Git push processing pipeline. A crafted repository URL could trigger arbitrary command execution on backend infrastructure, threatening source code integrity, repository secrets, and software supply chains. GitHub deployed mitigations and completed a patch rollout through coordinated disclosure before technical details became public.

Cyber Security News·Sep 14, 08:50 UTC · 2d agoVulnerabilityCVE-2026-38542

58

Using AI for Weapons Development

Anthropic report reveals Yemen-based actors used Claude Code to build guidance software for guided rockets and ballistic missiles.

Bruce Schneier highlights Anthropic's misuse disclosure describing a threat actor cell in northern Yemen running three weapons programs: a guided rocket with phone-class homing guidance, a 2,000+ km multi-stage ballistic missile, and the 'R2000' hypersonic glide vehicle set. The actors used Claude Code as a substitute for human engineers to write GNC software, integrate an open-source autopilot, tune controls, and run flight simulations, orchestrating multiple Claude instances in delegated roles. Safeguards blocked many requests but evasion tactics included hiding intent and splitting work across sessions; one guided rocket test-fire failed but no operational device was fielded.

Schneier on Security·Sep 14, 16:07 UTC · 2d agoAI safety & security in the wild

70

[webapps] EasyAppointments 1.5.1 - Blind SQL Injection

A proof-of-concept exploit for a blind SQL injection vulnerability in EasyAppointments 1.5.1 has been published on Exploit-DB.

Exploit-DB lists a public proof-of-concept exploit for a blind SQL injection flaw in EasyAppointments 1.5.1. The listing falls under the webapps category and enables reproduction of the injection. No in-the-wild exploitation or CVE identifier is stated in the listing.

Exploit-DB·Sep 1, 00:00 UTC · 16d agoExploit / PoC1

20

HazardAuditor: From Executable Threats to Safer Computer-Use Agents

HazardAuditor trains execution-grounded guard models for computer-use agents, improving safety verdict accuracy by up to 16.5 points.

HazardAuditor runs heterogeneous agents (Claude Code, Codex, Hermes, OpenClaw) in controlled environments and normalizes their interactions into a canonical event representation for cross-framework supervision. It introduces Guard Policy Optimization (GuardPO), which converts deterministic safety outcomes into sequence-level advantages and normalizes rationale and verdict regions so the safety decision becomes the effective optimization unit. Across multiple benchmarks and heterogeneous computer-use systems, HazardAuditor improves accuracy by up to 16.5 percentage points over the strongest prior guard model. Code, models, and evaluation artifacts are being released.

Hugging Face daily papers·Sep 13, 20:00 UTC · 3d agoAI safety & security

55

Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks

SAILS learns to select poison sets for LLM backdoor attacks, showing attack success ranges 3% to 80% at fixed poison counts across LLaMA-3-8B settings.

The paper shows existing backdoor evaluations that randomly sample a fixed number of poisoned examples severely underestimate worst-case vulnerability: across three LLaMA-3-8B settings, attack success ranges from 3% to 80% depending only on which poison set is chosen. SAILS formalizes poison selection as oracle-budgeted set optimization, learning a set scorer from a few hundred finetune-and-evaluate runs to rank millions of candidate sets and audit a small shortlist. It improves held-out attack success by 30 percentage points over the strongest influence baselines and transfers from small-scale to full-scale finetuning, extending to code-generation, agentic, and API-only backdoors.

arXiv cs.CR·Sep 14, 04:44 UTC · 2d agoAI safety & security 2 sources1

42

DeepSeek v4.1 Flash Is Now Our Best Hacking Model

DeepSeek V4.1 Flash achieves 11/11 code executions on Enclave's AI hacking benchmark for $4.65 across Grafana, Jenkins, and Nextcloud targets.

Enclave AI reports DeepSeek V4.1 Flash gained code execution on all 11 vulnerable targets while all four fixed controls held, costing $4.65 accepted ($5.14 total) with 268.3 million mostly cached input tokens. A path-level audit found six runs used the planned weaknesses, such as Jenkins credential-file abuse and a Nextcloud access-control confusion, while five runs exploited alternate routes in the Grafana and Jenkins test environments. The benchmark was hardened to check attack paths, not just outcomes, underscoring that hacking agents find the fastest exploitable route.

Hacker News · AI·Sep 16, 12:19 UTC · 14h agoAI safety & security 3 sourcesHN 54↑ · 7 comments

60

ZDI-26-616: Koha Eval Code Injection Remote Code Execution Vulnerability

ZDI disclosed CVE-2026-19780, a CVSS 8.8 authenticated eval code-injection flaw in Koha enabling remote code execution.

Zero Day Initiative advisory ZDI-26-616 describes a code injection vulnerability in the Eval component of Koha, the open-source integrated library system. A remote attacker must authenticate before injecting and executing arbitrary code on affected installations. ZDI assigned the flaw a CVSS 3.0 rating of 8.8.

ZDI Published Advisories·Sep 8, 05:00 UTC · 8d agoVulnerabilityCVE-2026-197801

35

ZDI-26-645: Fortinet FortiSandbox write_remote_backup_to_crontab cronValue Command Injection Remote Code Execution Vulnerability

ZDI publishes ZDI-26-645 for CVE-2026-84387, an authenticated command injection RCE in Fortinet FortiSandbox via crontab backup, rated CVSS 7.2.

Zero Day Initiative published advisory ZDI-26-645 describing a command injection flaw in Fortinet FortiSandbox's write_remote_backup_to_crontab function. Remote authenticated attackers can execute arbitrary code through the cronValue parameter. ZDI rated the issue CVSS 7.2 and assigned CVE-2026-84387.

ZDI Published Advisories·Sep 9, 05:00 UTC · 7d agoAdvisoryCVE-2026-84387

26

Re: Retrospective by 'gpg.fail' authors

GPG exploitation talk author clarifies a format-string 0day enabling code execution via printf %n writes and a polyglot PEM certificate payload.

Lexi Groves, author of the gpg.fail talk, clarified on oss-security that the first finding was an actual zero-day: a classic printf injection using %n for memory writes, with multiple X.509 certificates in one PEM file to re-enter and defeat ASLR before calling execv@plt. The payload executed the certificate itself, a polyglot file made by inserting a shebang and bash command into the PEM. A second finding was hash-collided by another party before the author could exploit it.

oss-security·updated Sep 16, 17:16 UTC · 9h ago·first Sep 16, 00:50 UTC · 1d agoResearch 8 sources

18

Cron Job Injection in Remote Backup

Fortinet FortiSandbox command injection flaw (CVSS 6.7) in remote backup cron jobs lets privileged attackers execute arbitrary code via crafted HTTP requests.

Fortinet advisory FG-IR-26-167 discloses a command injection vulnerability (CWE-77, CVSSv3 6.7) in FortiSandbox's remote backup cron job functionality. A privileged attacker can execute unauthorized code or commands via crafted HTTP requests. The advisory was revised on 2026-09-08.

Fortinet PSIRT·Sep 8, 07:00 UTC · 8d agoAdvisory

28

PoisonedRefresh: A Fileless Linux Rootkit That Injects PHP Web Shells Into F5 BIG-IP APM Server Memory

Sophos details PoisonedRefresh, a fileless Linux rootkit that injects a memory-resident PHP web shell into F5 BIG-IP APM after exploitation of CVE-2025-53521.

On September 8, 2026, SophosLabs published an analysis of Linux/Agnt-IC (dubbed PoisonedRefresh by ESET) found in compromised F5 BIG-IP Access Policy Manager environments. Initial access leverages CVE-2025-53521, an unauthenticated RCE in BIG-IP APM when an access policy is configured on a virtual server; F5 confirmed exploitation and links the activity to cluster c05d5254, while Shadowserver observed 795 exposed vulnerable endpoints. A first stage hidden in a modified umount binary modifies /usr/sbin/httpd and SELinux configuration and embeds itself in BIG-IP upgrade images for persistence. The second-stage ELF intercepts __libc_start_main, hooks apr_dso_load, and injects a PHP web shell into libphp memory via mmap manipulation, leaving no disk artifacts, and exposes a /bin/bash shell via a local UNIX domain socket instead of a TCP port.

Security Affairs·Sep 9, 08:50 UTC · 7d agoMalware in the wildCVE-2025-53521

78

Researcher shows how Claude Code can be tricked simply by asking it to summarize a website

Researcher wunderwuzzi showed Claude Code can be hijacked via prompt injection simply by asking it to summarize a website.

Security researcher Johann Rehberger (wunderwuzzi) demonstrated that Claude Code can be manipulated through prompt injection by simply asking it to summarize a website. Instructions embedded in fetched web content are executed by the agent, hijacking its behavior. The Register frames the finding as another demonstration of prompt injection risks in agentic coding tools that ingest untrusted web content.

The Register · Security·Aug 28, 20:50 UTC · 19d agoAI safety & security1

45

Linux Detection Engineering - Fileless Execution

Elastic Security Labs reproduces five Linux fileless execution patterns, including memfd_create staging and in-memory kernel module loads, and maps each to Elastic Defend rules.

Elastic Security Labs reproduced five Linux fileless execution patterns using its FENIX tooling: memfd_create staging, interpreter one-liners, deleted binaries, and in-memory kernel module loads. Each pattern is mapped to the Elastic Defend detection rules that catch it. The post is part of the team's ongoing Linux detection engineering series.

Elastic Security Labs·Sep 1, 14:26 UTC · 15d agoResearch

30

CS-Guard: Benchmarking LLM Guardrails for Code Generation Security

CS-Guard benchmark shows LLM code-generation guardrails fail widely, with ~50% jailbreak ASR text-to-code and up to 100% code-to-code.

Researchers introduce CS-Guard, the first systematic benchmark for evaluating LLM guardrails for code generation security, covering text-to-code (1,000 malware-generation prompts, 7 jailbreak attacks, and a novel fictional scenario attack) and code-to-code (331 prompts across infilling, completion, and translation). They evaluate 9 guardrails across seven LLMs, finding average jailbreak attack success rates around 50% for text-to-code and 14.4% to nearly 100% for code-to-code. The fictional scenario attack achieves ASR close to 100% across many guardrails, raising reliability concerns for real-world software development. The benchmark and data are released publicly.

arXiv cs.CR·Sep 9, 06:50 UTC · 7d agoAI safety & security1

45

Flextype v1.0.0-alpha.3 Stored Expression Injection Enables PHP Remote Code Execution

Flextype CMS v1.0.0-alpha.3 stored expression injection exposes the mutable registry object, enabling stored PHP remote code execution.

Flextype CMS v1.0.0-alpha.3 evaluates attacker-controlled entry fields as expressions during entry retrieval when global expression processing is enabled. The expression environment exposes the application's mutable registry() object, which attackers can manipulate. Combined with the PHP entry directive, this enables stored PHP remote code execution from crafted entry content. The flaw was disclosed on the Full Disclosure mailing list on September 3, 2026.

Full Disclosure·Sep 4, 00:13 UTC · 13d agoVulnerability 8 sources

34

BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure

BenchShield uses lifecycle-model-backed instrumentation to detect reward hacking in LLM-agent benchmarks, lifting full-chain recall to 77-100% at up to 65% lower cost.

The framework grounds reward-hacking detection in a finite lifecycle model of an evaluation's reward-relevant events, combining a static phase-aware taint analysis with runtime infrastructure-side evidence attribution. Evaluation used a human-labeled corpus of 456 adjudicated trajectories drawn from more than 31,000 public agent runs across three benchmarks. BenchShield improves full-chain recall from 23-94% to 77-100% and same-vector coverage from 16-56% to 43-78%, cuts per-task cost by up to 65%, and achieves 96% accuracy detecting reward hacking at runtime.

arXiv cs.CR·Sep 10, 03:10 UTC · 6d agoAI safety & security1

42

Cursor Security Bug Allowed Repositories to Execute Commands Before Trust Verification

Cursor fixed a pre-trust bug letting untrusted repositories execute commands, then closed the report as informative.

A security flaw in the Cursor editor allowed repositories to execute commands before the user completed workspace trust verification. Cursor fixed the pre-trust code execution path within three days of receiving the report. The vendor then closed the report as informative, disputing the severity of the behavior.

Infosecurity Magazine·Aug 11, 14:30 UTC · Aug 11, 2026Vulnerability

50

MasterControl Seventeen Every Time

Governed enterprise analytics study shows deterministic policy execution matched 110/110 answer-and-evidence contracts while runtime agent planning matched none.

The paper studies a governed approach where a language model interprets the question while deterministic policy selects and runs a pre-approved analytical program returning results and evidence. Across 440 runs, three 8B models generated SQL and selected tools at runtime, while Qwen3-8B only interpreted intent and policy executed the approved program. None of 330 runtime-planning episodes satisfied the full answer-and-evidence contract, whereas the policy-executed analyzer matched 110 of 110. The authors note this is configuration-specific and expressiveness is preserved via relational operations, aggregation, comparison, windows, ranking, and similarity with replayable results.

Hugging Face daily papers·Sep 1, 20:00 UTC · 15d agoAI research

24

[webapps] Payload CMS 3.72.0 - Blind SQL Injection

A proof-of-concept exploit for a blind SQL injection vulnerability in Payload CMS 3.72.0 has been published on Exploit-DB.

Exploit-DB lists a public proof-of-concept exploit for a blind SQL injection flaw in Payload CMS 3.72.0. The listing falls under the webapps category and allows reproduction of the injection. No in-the-wild exploitation or CVE identifier is stated in the listing.

Exploit-DB·Sep 1, 00:00 UTC · 16d agoExploit / PoC1

25

$536 and 8 Hours: AI Learns to Attack a Different PLC

Forescout used Claude to port a WAGO PLC exploit for $536 in 8 hours, and an AI-generated payload later permanently bricked the test device.

Forescout researchers used Claude Code with Ghidra, terminal access, and physical hardware to port CVE-2021-31886, a pre-authentication buffer overflow in the Nucleus FTP server, from a WAGO 750-852 PLC to the WAGO 750-831 without source code or debugger access. The final RCE development stage cost $535.74 in API fees over an 8-hour, 32-minute session (2.6k input and 1.3M output tokens) and required heavy researcher guidance. Claude produced working ICMP and UDP beacon exploits in 12 minutes after identifying that normal FTP command completion was overwriting its shellcode, fixed by omitting the CRLF terminator. A follow-up session extending the payloads toward a C2 implant wrote to flash-mapped memory and permanently bricked the PLC, underscoring the risks of autonomous agents operating against physical infrastructure.

Security Affairs·Sep 2, 13:50 UTC · 14d agoResearchCVE-2021-318861

55