opteo

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md instructs the agent to list and run Membrane actions and to proxy arbitrary requests to the Opteo API (e.g., "membrane action run ..." and "membrane request CONNECTION_ID /path/to/endpoint"), which causes the agent to fetch and interpret untrusted user-generated Opteo account data and use it to decide and perform follow-up actions.