audit

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches user-generated issue content via "issue references: fetch title and body via gh issue view" in the Phase 1 supporting-context gathering and also cross-references open issues during Phase 4, meaning untrusted public GitHub content is read and fed into analysis prompts and synthesis.