add-github

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md configures GitHub webhooks and a channel so the agent receives and responds to PR and issue comment events (user-generated public GitHub content) — see "Credentials", "Wiring", and "Channel Info" — meaning untrusted third-party comments can be read and drive the agent's actions.