fix-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 and reads public, user-generated issue content (e.g., "gh issue view $ARGUMENTS --json title,body,labels,assignees,comments" in Phase 1 / fix-phases.md and related STEP 1/Understand Issue steps), and that content is consumed as core input for RCA and decision-making, exposing the agent to untrusted third-party text that could carry indirect prompt injections.