pitchlane

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to run Membrane actions and proxy arbitrary requests to the Pitchlane API (e.g., "membrane action run ..." and "membrane request CONNECTION_ID /path/to/endpoint"), which causes the agent to fetch and interpret data from a third-party service that can include untrusted/user-generated content from prospects.