xiaohongshu

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

• Third-party content exposure detected (high risk: 0.90). The skill's Engagement workflow explicitly opens https://www.xiaohongshu.com/notification and instructs the agent to read user comments/replies and follower profiles (user-generated, untrusted third-party content) and then compose responses or follow actions, so third-party content can directly influence the agent's actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs cloning and running code from https://github.com/nowork-studio/md2red (git clone https://github.com/nowork-studio/md2red and python3 md2red.py), which fetches remote code that is executed as a required runtime dependency.