55
55
55
42
30
30
30
TrajMark: Ownership Attribution and Segment-Level Tamper Localization for Coding-Agent Trajectories
Researchers introduce TrajMark, a training-free watermarking framework for coding-agent trajectories that recovers ownership, detects 95.5-100% of edits, and localizes tampered regions.
TrajMark is a training-free, symmetric-key, visible-only watermarking framework for coding-agent trajectories that separates robust ownership attribution from fragile local integrity verification. A sparse owner layer encodes a six-bit deployment identifier by rewriting keyed READ actions into masked linear equations, while a localization layer inserts linked Q12 seals that commit to protected critical-action segments. Across three coding-agent frameworks and three LLMs, it recovers the exact owner in all clean full-watermark batches, detects 95.5%-100% of single-site edits, and localizes 95.8% of random corruptions to an accepted protocol region. Owner marking adds no trajectory actions and matched Pass@1 is 26.9% versus 26.3% for unwatermarked runs.
30
When the Whole Company Adopts AI: What It Does to Your SOC
Analysis of 16.9 million SOC alerts finds AI-related alerts at 0.43%, growing 685% since February, with 94.1% noise and 0.02% real attacks.
A review of roughly 16.9 million SOC alerts found about 73,000 (0.43%) were AI-related, a share that grew 685% between February and June 2026. Of AI-related alerts, 94.1% were noise, 5.8% genuine risks, and 0.02% real attacks; 79.8% received benign verdicts, 81.7% were automatically suppressed, and only 5.4% reached a human analyst. The only confirmed attacks were phishing campaigns that weaponized AI brand names as lures, while developer coding agents spawning shells and reading credential stores routinely tripped detections written before AI agents existed.
45
35
30
Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
Malicious .git core.fsmonitor configs let attacker code run in AI coding agents like Claude Code and Codex; four of eight flaws remain unpatched.
Manifold Security disclosed eight flaws across seven command-line AI coding agents where a repository's Git core.fsmonitor configuration causes agent-spawned commands to execute attacker code outside the sandbox and without approval prompts. Fixes shipped for goose (CVE-2026-72718, CVSS 4.0 score 7.0), Claude Code on one path, and Cursor, while Hermes Agent, Qwen Code, Grok Build, and a second Claude Code path were still unpatched as of September 1. OpenAI issued three CVEs for the same class in Codex, including CVE-2026-19592, and prior related bugs include CVE-2021-43891 in Visual Studio Code and CVE-2022-24346 in JetBrains IDEs. Exploitation requires the repository to arrive with its .git directory intact, such as via archives, shared drives, or USB sticks rather than an ordinary clone.
68
42
42
55
30
30
The Self-Expanding Stolen Inference Supply Chain: An AI Agent Harvesting and Re-Serving LLM Access, (Fri, Sep 11th)
An autonomous coding agent harvested LLM API access from poorly secured gateways and aggregated stolen inference capacity behind a self-hosted gateway
A SANS researcher observed a semi-autonomous coding agent finding weakly secured LLM resale gateways via FOFA queries, creating trial accounts with temporary emails and CAPTCHA solving, and exploiting weak authorization such as client-supplied group_id fields. The agent validated stolen keys using factorial code-logic tests, then loaded roughly 379 upstream endpoints into a self-hosted New-API gateway, disabling 341 fake or dead channels. Five model names including claude-opus-5 and gpt-5.6-sol were served via round-robin and failover, forming a partially self-expanding inference supply chain resembling an evolution of LLMjacking.
68
60
ZDI-26-546: Flowise Airtable_Agent Code Injection Remote Code Execution Vulnerability
ZDI discloses an unauthenticated code injection remote code execution flaw in Flowise's Airtable_Agent (CVE-2026-69264, CVSS 9.8).
ZDI advisory ZDI-26-546 describes a code injection vulnerability in the Flowise Airtable_Agent that allows remote attackers to execute arbitrary code. No authentication is required to exploit the flaw, which carries a CVSS rating of 9.8 and is assigned CVE-2026-69264. Flowise deployments exposing the vulnerable agent component are at risk of full server takeover.
42
60
60
60
Hackers Target Claude, Cursor and Codex AI Agents to Steal Tokens and Prompt Histories
Gen Digital found infostealers like Amatera and Remus stealing AI coding agent tokens, prompt histories, and MCP configs from infected Windows and macOS machines.
Gen Digital analysts observed Amatera and Remus detections among tens of thousands of protected Windows users over three months, with Amatera targeting Cline and Continue data and Remus targeting Claude, Cursor, and OpenCode. CallbackBeaver added Cursor and Claude to its collection scope with more than 5,000 samples in 30 days, while macOS-focused Djinn Stealer has been associated with Claude, Codex, Gemini, Cline, OpenCode, and Kilo. The stealers harvest access and refresh tokens, prompt histories, and MCP configuration files that can expose source control, ticketing, databases, cloud resources, and sensitive project context for follow-on fraud. Many stealers add targets via remotely managed rules, meaning this is an adaptation of existing infostealers rather than a new vulnerability in the AI tools themselves.
58
60
Week in review: AiTM phishing kit used to hijack AWS accounts, year-long malware campaign targets HR
60
47
50
55
55
60
Product showcase: Doppler secures secrets for humans, pipelines, and AI agents
Doppler's secrets management platform centralizes credentials for engineers, CI/CD pipelines, MCP servers, and AI agents with runtime injection and dynamic secrets.
Doppler stores API keys, database URLs, tokens, and certificates in a single control plane and injects them at runtime, replacing .env files for human and machine identities including AI agents. It supports OIDC with short-lived identity tokens for Azure, AWS, and GCP, dynamic secrets scoped and time-boxed to single sessions, SCIM provisioning, 50+ integrations, and an MCP server that lets agents request configurations natively. Permissions are enforced at each layer so raw secrets stay out of logs, prompts, and model context, with versioning, rollback, SIEM log forwarding, and cloud or on-prem deployment.
26
30
GTIG AI Threat Tracker: From Prompting to Autonomy – The Evolution of Adversarial AI
GTIG's Q2 2026 tracker shows adversaries adopting agentic AI workflows, including credential harvesting in under six hours and supply chain attacks by UNC6780.
Google Threat Intelligence Group's Q2 2026 report documents adversaries moving from basic prompting to agentic AI workflows and automation, including a cloud compromise followed by agent-enabled mass credential harvesting executed in under six hours. It tracks financially motivated actor UNC6780 (TeamPCP) conducting large-scale open source supply chain compromises across PyPI, npm, and Docker Hub since March 2026, deploying credential stealers. The report also highlights growing targeting of proprietary AI models, source code, prompts, and API credentials, plus LLMJacking practices where adversaries steal developer credentials or hijack cloud infrastructure to run unauthorized AI workloads.
65
42
55
60
55
ZDI-26-545: Flowise CSV_Agent customReadCSV Code Injection Remote Code Execution Vulnerability
ZDI discloses CVE-2026-69256, a CVSS 8.8 code injection in Flowise CSV_Agent customReadCSV allowing authenticated remote attackers to execute arbitrary code.
ZDI advisory ZDI-26-545 describes a code injection vulnerability in Flowise's CSV_Agent customReadCSV functionality, tracked as CVE-2026-69256 with a CVSS score of 8.8. It allows remote attackers to execute arbitrary code on affected Flowise installations. Authentication is required to exploit the vulnerability.
40
Staying Ahead of Adversarial AI Through Agentic Source Code Review
Google Threat Intelligence details an agentic AI pipeline with human expert oversight to review source code and outpace AI-enabled attackers.
Google Threat Intelligence researchers argue that adversaries' misuse of AI raises the risk of data theft and extortion when proprietary source code is exposed. They describe a structured agentic source code review pipeline that combines AI models with skeptical validation steps and injected human domain expertise. The team reports a leap in efficacy in finding vulnerabilities before adversaries can exploit them.
45