skill-preflight

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

• Third-party content exposure detected (low risk: 0.10). This skill’s required workflow only reads first-party repository artifacts (skills/ and .claude/agent markdown, plus skills/shared/skill-index.md) via filesystem tools and greps for keywords derived from the user’s request, without ingesting arbitrary outsider-authored free text from an external feed/queue without selecting an item.