define-variables
Warn
Audited by Snyk on May 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's required pipeline (SKILL.md Tier 2 "Targeted
/search-lit" and Tier 3 "/verify-refson the accumulated BibTeX") explicitly instructs the agent to fetch and read literature from public third‑party sources (PubMed/CrossRef) as part of its workflow, and those external results are used to choose definitions/cutoffs that will directly influence downstream decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata