paperform

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 using "membrane action run" and the "membrane request" proxy to fetch data from the PaperForm API (e.g., forms and submissions), which are untrusted/user-generated third-party contents the agent would read and 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 Membrane CLI via npm/npx (e.g. "npm install -g @membranehq/cli" and "npx @membranehq/cli@latest"), which fetches and executes remote code from the npm registry (e.g. https://registry.npmjs.org/@membranehq/cli) at runtime, so it is a runtime external dependency that executes remote code.