Prompting

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 updating and syncing Fabric patterns from upstream (via the update-patterns.sh / fabric -U flow) and extracting YouTube transcripts (fabric -y "https://youtube.com/..."), meaning the skill can pull and then read/apply public, user-generated third‑party content (Fabric updates and YouTube transcripts) that can directly influence prompt templates and agent behavior.