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 web and "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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 08:08 AM
Issues
1