xiaohongshu-creator

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

• Third-party content exposure detected (medium risk: 0.30). The workflow allows users to submit arbitrary text, files, and web URLs to be processed and checked for prohibited words, which the agent ingests at runtime.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill executes runtime scripts that fetch data from external APIs hosted on a third-party domain (redfox.hk) requiring user authentication, representing a common unofficial operational dependency.