investigate-ci

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

• Third-party content exposure detected (high risk: 0.85). Yes: step 0 reads an outsider-authored GitHub issue body/comments via gh issue view ... --json ...body,comments, and step 1/4 then fetches outsider CI report JSON/logs from user-supplied PR/S3 URLs (public web content) whose contents are printed/parsed and thus become LLM-readable context.