snapdocs

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 call and proxy arbitrary Snapdocs API endpoints (see "Proxy requests" and the membrane request examples) which fetch user-generated/untrusted third‑party content that the agent is expected to read and could materially influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill requires installing and running the Membrane CLI via "npm install -g @membranehq/cli" (https://www.npmjs.com/package/@membranehq/cli), which fetches and executes remote code at runtime as a required dependency.