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
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 06:42 PM