research
Warn
Audited by Snyk on Mar 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: 1.00). The SKILL.md workflow explicitly requires using the browser-use skill to search and read exact URLs (see "For examining any web sites or searching the web, use
browser-useskill" and the resources files like resources/sites-health-and-nutrition.md which list many public Substack/blog/news sites), so the agent will fetch and interpret untrusted public web content that can materially influence its conclusions and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata