npm

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

• Third-party content exposure detected (high risk: 0.75). The required workflow uses ClawLink to query NPM (e.g., registry search/get metadata/changes) at runtime, which ingests public npm registry content (outsider-authored web data) into the agent’s LLM context via the tool outputs.

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" at runtime, which fetches and executes remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli) and is required for the skill to operate, so the external content can execute code and control agent actions.