skill-intake

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the intake workflow iterates over “Open issues or PRs” via gh issue list/gh pr list (or bd ready/bd blocked) and then uses that outsider-authored issue/PR text to categorise/verify and generate the brief, so the required runtime ingests community-submitted free text from these queue items.