fabric

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and process arbitrary web and YouTube content (e.g., "fabric -u 'URL' -p [pattern]", "fabric -y 'YOUTUBE_URL' -p [pattern]" and "curl -s 'https://...' | fabric -p analyze_claims"), so untrusted public/user-generated pages/transcripts are ingested and interpreted by patterns (including "extract_instructions") that can materially influence subsequent analysis and actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires cloning/updating the Fabric repository at runtime (git clone https://github.com/danielmiessler/fabric.git) and uses the fetched repository's pattern files to drive/choose prompts, so the external URL directly controls agent instructions and is a required runtime dependency.