tapform

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 actions and proxy requests via Membrane to the Tapform API (see "Running actions" and "Proxy requests"), which will fetch and ingest Tapform data (e.g., form submissions and user-generated content) that the agent is expected to read and could materially influence its decisions.