bmad-os-review-pr

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and checks out PRs from GitHub using gh pr checkout/view/diff and the prompts/instructions.md states to "Pass the full PR diff as context" to subagents, so untrusted, user-generated PR content from public repos is ingested and can directly influence the agent's analysis and actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires a user-provided GitHub PR URL (e.g., https://github.com/owner/repo/pull/123) which is fetched at runtime via gh pr checkout/gh pr view and the returned PR diff is injected into spawned subagents as model context, so external content directly controls the agent's prompts.