fabric

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and processes arbitrary public web and user-generated content (e.g., "fabric -u 'https://example.com/blog-post' -p summarize", "fabric -y 'https://youtube.com/watch?v=...' -p youtube_summary", and "curl -s 'https://...' | fabric -p analyze_claims"), so the agent will read/interpret untrusted third-party pages/transcripts and could be exposed to indirect prompt injection.