simplecast

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 use Membrane action list/run and proxy requests to fetch data from the Simplecast API (e.g., episode metadata and show notes), which are public, user-generated third‑party contents the agent will read and that could influence subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill requires installing and running the remote Membrane CLI (npm install -g @membranehq/cli and npx @membranehq/cli@latest), which fetches and executes third-party code at runtime and is presented as a required dependency.