fabric-patterns

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md and references/piping-idioms.md explicitly instruct using fabric's built-in fetchers (e.g., "fabric -u "https://..."", "fabric -y "https://youtube...\"", Spotify/podcast flags and comments/transcript options) to scrape public URLs and user-generated content and then run patterns on that content, so the agent will read and act on untrusted third‑party content that can materially influence subsequent pattern execution and decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs using the fabric CLI which can fetch and update pattern system prompts from the remote repository (https://github.com/danielmiessler/fabric) at runtime (e.g., via fabric -U and pattern loading), so external content from that URL can directly control the agent's prompts.