comm-lit-review-claude-single
Warn
Audited by Snyk on Mar 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: 0.80). This SKILL.md explicitly requires searching and ingesting open/public third-party sources (see "Source Selection" default including
weband "Step 1: Search External Primary Sources" listing ieeexplore, sciencedirect, dl.acm.org and "broader web"), and it directs the agent to read/interpret those pages and extract paper-level facts that materially drive synthesis and next actions, so untrusted third-party content could influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata