compliance-officer

Warn

Audited by Snyk on Feb 21, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill's agent instructions in references/instructions.md explicitly say it accepts a URL and will "fetch with WebFetch" (e.g., "Review Content" and "Check Privacy Policy" modes), and claw.json grants network permission, so the agent will ingest arbitrary public/user-provided webpages which can directly influence its compliance decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 06:14 AM