{
  "id": 1618,
  "url": "https://ainowinstitute.org/publications/friendly-fire-exploit-brief",
  "title": "Friendly Fire: Hijacking Defensive Cyber AI Agents for Remote Code Execution",
  "summary": "Exploit Brief We are revealing a proof-of-concept exploit that enables remote code execution in Anthropic’s Claude Code CLI (with Claude Sonnet 4.6 & 5, Opus 4.8) and OpenAI’s Codex CLI (with GPT-5.5) when employed to defensively assess the security of an open-source or third-party library. Our attack only requires an out-of-the-box configuration of Claude Code […] The post Friendly Fire: Hijacking Defensive Cyber AI Agents for Remote Code Execution appeared first on AI Now Institute .",
  "authors": "Boyan Milanov",
  "category": "org",
  "topics": "military-security,agents-autonomy",
  "orgs": "openai,anthropic",
  "regions": null,
  "published_at": "2026-07-08T12:30:08.000Z",
  "fetched_at": "2026-07-14T16:04:12.223Z",
  "source_slug": "ai-now",
  "source_name": "AI Now Institute",
  "source_homepage": "https://ainowinstitute.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1618",
  "original_url": "https://ainowinstitute.org/publications/friendly-fire-exploit-brief",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}