coda

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.65). The required workflow uses ClawLink to access the user’s connected Coda account and then runs “actions coda” which fetches Coda doc/table content and returns it to the agent as readable text (outsider-authored content from other users’ Coda pages/tables can be ingested at runtime via the Coda API through the CLI).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill invokes "npx @useclawlink/cli" at runtime, which fetches and executes remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli) and relies on ClawLink (https://claw-link.dev) for functionality, so it has a required runtime dependency that executes external code.