novelty-check
Warn
Audited by Snyk on Apr 19, 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). This skill's Phase B requires WebSearch and WebFetch of public third-party sources (explicitly arXiv, Google Scholar, Semantic Scholar) and instructs the agent to read abstracts and related-work to make novelty decisions, which exposes it to untrusted, user-contributed web content that can influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata