fixing-pr-comments

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Detect & Fetch" workflow (see the GraphQL query in SKILL.md that fetches pullRequest.reviewThreads and comments) ingests untrusted, user-generated GitHub PR review comments which the agent is expected to read, triage, and act on (FIX/RESOLVE/CLARIFY), so those third-party contents can materially influence tool use and decisions.