build-from-issue

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches GitHub issue bodies and user comments (Step 1 "Fetch the Issue" and Step 2 "Fetch and Classify Comments") and uses those human-authored, public issue/comments to determine actions and change plans, so untrusted third-party content can influence the agent's decisions.