afk-loop

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

• Third-party content exposure detected (high risk: 0.85). The workflow explicitly fetches outsider-authored issue tracker content (issue title/body/comments and PR comments) at runtime in the implementer/reviewer/fixer prompts (“Fetch issue {{ISSUE_ID}} from the tracker… It is your spec — title, body, and comments all count” and “Fetch the PR's comments”), which is free text written by others and can be used for indirect prompt injection.