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 reads and acts on public, user-generated GitHub issue content (e.g., Phase 1: "gh issue view $ARGUMENTS --json ..." and similar-issue-finder.sh / references/similar-issue-search.md calling "gh issue list"), and that content is used by agents to form hypotheses and drive fixes, so untrusted third-party text can materially influence tool use and next actions.