regulatory-guard
Warn
Audited by Snyk on Jul 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.82). The skill’s required runtime workflow includes live page inspection/network capture and reading “privacy policy text, cookie banner UX… third-party network calls” (e.g., fetching a target URL and extracting page/headers), which will ingest outsider-authored free text from the audited website into the agent’s LLM context via the browser/HTTP-gather stage.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata