fabric-ai

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly includes Content Types and Commands that fetch and process arbitrary public URLs/YouTube transcripts (e.g., "-y ", "-u " and the example "fabric -y -p extract_wisdom ..."), so the agent is expected to read untrusted, user-generated web content that can influence its subsequent actions.