admiralty-system
Warn
Audited by Snyk on May 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). SKILL.md's workflow explicitly requires extracting and rating posts from public user-generated sources (e.g., dark‑web/forum posts like Exploit[.]in and BreachForums, vendor blogs, social media) and tells the agent to cross‑check via archived snapshots/Wayback/FOFA and pull samples, so the agent is expected to fetch and interpret untrusted third‑party content that can materially influence its decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata