agent-security-audit

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md includes a safe-fetch pattern (safe-fetch.sh) that uses curl to retrieve arbitrary external URLs and then processes that untrusted web content as part of the agent's workflow (sanitize_content, detect_injection, validate_memory_write), so third‑party pages could influence decisions or actions.