documint

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 fetch and proxy data from the Documint API (see "Popular actions" like get-template/list-templates and the "Proxy requests" section using membrane request / membrane action run), which will return user-generated templates/documents from a third-party service that the agent must read/merge and that can influence subsequent actions.