clerk-testing

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly instructs the agent to "WebFetch the appropriate URL from decision tree above" (the public Clerk docs URLs like https://clerk.com/docs/...), so the agent will fetch and follow instructions from open, third‑party web pages which can materially influence its actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly instructs a runtime "WebFetch" of external Clerk documentation (e.g., https://clerk.com/docs/guides/development/testing/overview) and to "follow official setup instructions," meaning fetched remote content is used at runtime to control the agent's setup/instruction flow.