pr-descriptions

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

• Third-party content exposure detected (high risk: 0.70). The skill instructs the agent to read and verify PR bodies via GitHub commands (e.g., gh pr view --json body and gh api repos/OWNER/REPO/pulls/...), which are user-generated content on GitHub and therefore untrusted third-party input that could contain injected instructions.