audit-ready-pr-reviewer

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

• Third-party content exposure detected (high risk: 0.85). The required workflow is driven by reviewing a GitHub/GitLab PR and posting comments, which implies the agent reads PR content authored by outsiders (e.g., PR description/code diffs) into the LLM context via the review-pr.js runtime path; no exclusion in SKILL.md indicates otherwise.