novelty-check
Warn
Audited by Snyk on Jul 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md:24-35 requires runtime WebSearch/WebFetch of external web content (e.g., arXiv/Google Scholar/Semantic Scholar abstracts), which is outsider-authored free text that is then included in the Phase C prompt sent to the LLM.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata