simplero

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly lets the agent fetch and run actions against a third-party Simplero account (e.g., "membrane request CONNECTION_ID /path/to/endpoint" and action runs that return contacts, emails, courses), so the agent will read user-generated/untrusted Simplero data as part of its workflow which could influence subsequent actions.