book-review
Warn
Audited by Snyk on Mar 10, 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's Phase 4 ("Supplement with Web Research") and the "Links and Sources" instructions explicitly direct the agent to search for and read external web sources (academic sources, author interviews, Substack/blogs and real URLs) so it will fetch and interpret public third-party content that can influence drafting and decisions.
Audit Metadata