discussions

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 triages user-generated GitHub Discussions using the helper command gh-manager discussions list --repo owner/name (see "Step 1: Check for Discussions" and helper commands) and then drafts/post comments and closes threads, so untrusted public discussion content is read and can materially influence the agent's actions.