researcher

Warn

Audited by Snyk on Feb 22, 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). The skill explicitly requires fetching and reading primary documents from open public third-party sources (via /document-hunter and WebFetch) and lists sites like DocumentCloud, CourtListener/RECAP, Scribd, Justia and news archives in free-sources.md, and those untrusted/user-provided documents are parsed and used to drive verification, evidence chains, and follow-up actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 22, 2026, 06:45 AM