teach
Warn
Audited by Snyk on Aug 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill’s runtime explicitly performs web search/research and adds fetched findings into
RESOURCES.md(and then cites them in lessons), so outsider-authored free text from arbitrary web pages can be ingested at generation time without selecting a specific trusted item first.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata