advise

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

• Third-party content exposure detected (medium risk: 0.30). In the github advise skill, outsider-authored free text can be ingested at runtime via GitHub content that is read while advising (e.g., fetched repo descriptions, issue/PR bodies, and other GitHub content), which the workflow treats as untrusted data and explicitly guards against being followed as instructions.