search-prior-art
Warn
Audited by Snyk on Feb 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to search and ingest open/public third-party sources — e.g., Google Patents, USPTO, Espacenet, Google Scholar, arXiv, GitHub, product web pages, and the Wayback Machine (Steps 2 and 3) — which are untrusted/user-generated sources whose content the agent must read and that can materially influence search conclusions and next actions.
Audit Metadata