oh-review

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 interprets user-generated GitHub content (PR body via gh pr view ... --json body and the linked issue via gh issue view <N> --json body) and uses the issue's acceptance criteria as the authoritative spec to decide reviews and whether to approve/request changes, so untrusted third-party text can directly influence agent actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill calls gh issue view <N> at runtime to fetch the linked GitHub issue (e.g., https://github.com///issues/ or the GitHub API endpoint https://api.github.com/repos///issues/), and the issue body is explicitly used as the source-of-truth to generate and control the agent's review prompts — a runtime external dependency that directly controls prompts.