fathom

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 “run shell commands” that fetch and read Fathom action data (and likely page/content needed to execute actions) from Fathom/connected third-party services at runtime, which can include outsider-authored free text that the agent ingests into its LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to run npx @useclawlink/cli (which downloads and executes the remote npm package @useclawlink/cli at runtime from https://www.npmjs.com/package/@useclawlink/cli), so external code is fetched and executed and is required for operation.