issue-implement

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and parses user-generated GitHub issue content (e.g., via "gh issue view" in Step 1 and related gh API calls in Steps 2–3 and Step 7's acceptance-check) and uses that content to decide whether to proceed, abort, or perform tool actions, exposing it to untrusted third-party input that could carry indirect prompt injection.