gist

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 connect to a "gist" connector and use Membrane CLI commands like "membrane action run" and "membrane action list" to retrieve and operate on Gist data (public GitHub gists), which are untrusted, user-generated third-party content that the agent would read and could influence subsequent actions.