artilleryio

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

• Third-party content exposure detected (high risk: 0.80). The skill’s SKILL.md explicitly instructs the agent to call third-party Artillery.io endpoints via Membrane (e.g., "membrane action list", "membrane action run", and "membrane request CONNECTION_ID /path/to/endpoint"), meaning the agent will fetch and read API responses from an external service (potentially user-generated/untrusted) and use those responses (action objects/input schemas) to decide subsequent actions.