Depi's Research Team reported a chain against openai/codex that began with a prompt injection in a GitHub issue and ended in a persistent backdoored workflow. Bugcrowd lists it as accepted and fixed, with a Bugcrowd priority of P1.
Depi's Research Team reported a chain against openai/codex that began with a prompt injection in a GitHub issue and ended in a persistent backdoored workflow. Bugcrowd lists it as accepted and fixed, with a Bugcrowd priority of P1.
Forever Security reports flaws in the browsers embedded in five AI coding assistants, from code execution in Cursor to file reads in Claude Desktop, Codex and VS Code. Per its 29 October report, two remain unpatched.
Symantec says an unauthorized relay service installs genuine Codex and Claude Code CLIs, then turns off Codex's sandbox and routes every request through its own servers. About a dozen organizations are affected.
Forever Security found a malicious AGENTS.md in a customer's Downloads folder and reproduced the attack on OpenAI Codex and Claude Code in lab tests. Success rates were about 90% for Codex and about 50% for a Claude Code variant.
Researchers at Concordia University tested Cursor, Claude Code, and Codex Desktop against a benchmark of malicious GitHub issues. Two thirds of the attacks penetrated all guardrails, with LLMs — not agent frameworks — doing most of the blocking.
Sophos X-Ops telemetry analysis shows Claude Code, Cursor, and OpenAI Codex triggering behavioral EDR detection rules built to catch human attackers. Credential access patterns account for 56.2% of blocked activity -- agents using the same Windows DPAPI technique as Redline stealer.