mojo-helpdesk

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows the agent making proxied API calls to Mojo Helpdesk (e.g., "membrane request CONNECTION_ID /path/to/endpoint" and actions to fetch/manage Tickets/Comments/Users), which pulls untrusted, user-generated third‑party content that the agent is expected to read and can materially influence its actions.