review

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md’s required workflow includes “Spec Auto-Detection” in PR mode that extracts PR description/body and linked GitHub issue bodies (outsider-authored free text) via gh pr view / gh issue view, which is then assembled into the triage context and passed into reviewer prompts for LLM analysis.