research
Warn
Audited by Snyk on Aug 10, 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). SKILL.md instructs the agent to actively search and read outsider-authored free text from sources like GitHub code/repos, arXiv papers, and vendor tutorials/blogs/forums at runtime (“Then prior art” → “Go find them… GitHub… Read the real source”).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata