trio

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs using "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint" to fetch data from the Trio API (e.g., Meeting Notes, Contacts), so the agent will ingest user-generated, third-party content from Trio that could materially influence actions.