productlane

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 using Membrane to run actions and proxy requests (e.g., "membrane action list/run" and "membrane request CONNECTION_ID /path/to/endpoint") to fetch Productlane data such as cards and comments (user-generated content) from the third-party Productlane API, which the agent is expected to read and could materially influence subsequent actions.