travel-planning

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads user reviews, travel notes, and posts from Xiaohongshu and third-party travel platforms via CLI commands, which ingest outsider-authored free text without pre-filtering or direct item selection.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs cloning an unverified third-party GitHub repository (https://github.com/better-world-ai/x-cli) and building executables from it at runtime, representing a weak/unknown operational dependency.