stack-exchange

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

• Third-party content exposure detected (high risk: 0.85). At runtime, the skill’s “Stack Exchange” actions will fetch and ingest Stack Exchange page/content (e.g., question/answer text, comments, issue-like threads) authored by other users via browser/OAuth through ClawLink, which becomes readable free text in the agent’s LLM context—an outsider source.

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 will fetch and execute remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli), so it depends at runtime on external code execution.