Severity: HighResearchPrompt injection
AI Code Analysis Agents Can Be Manipulated to Execute Malicious Payloads
Global
Live intelligence. Items are aggregated from public sources and summarised automatically. Always verify against the linked source before acting.
Researchers from AI Now Institute have demonstrated that autonomous AI agents designed to analyze code for security vulnerabilities can be tricked into executing attacker-controlled code on the analyst's own system. The attack, dubbed "Friendly Fire," affects Claude Code and Codex when operating in autonomous approval mode, exploiting the agent's trust in its own decision-making.
What to do
Disable autonomous code execution modes in AI agents and require explicit human approval before running any code discovered during analysis.
Mapped framework pillars
Sources
#prompt injection#agentic AI#code agents#autonomous execution#jailbreak