boloforms

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md explicitly instructs using Membrane to run actions like "get-form-responses" and to proxy arbitrary requests to the Boloforms API (via the "membrane request CONNECTION_ID /path/to/endpoint" example), which causes the agent to fetch and read untrusted, user-generated form submissions and documents that could materially influence subsequent actions.