bmad-os-review-pr

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and checks out PRs from GitHub using gh pr checkout/view/diff and passes the full PR diff as context to subagents (steps 0.2, 0.3, 1.1 and 1.2), which are untrusted, user-generated third-party contents that the agent reads and uses to drive tool actions and posting — creating a clear vector for indirect prompt injection.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches PR diffs from GitHub at runtime (e.g., https://github.com/owner/repo/pull/123 via gh pr view/gh pr diff/gh pr checkout) and injects that fetched content directly into subagent prompts, so external content can control the agent's instructions.