kuaishou-comment-scraper

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

• Third-party content exposure detected (medium risk: 0.30). The workflow monitors and scrapes comments from Kuaishou video posts and web pages, which contain outsider-authored free text accessed via browser automation.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to automatically download and install an external skill from a GitHub repository via a third-party website URL during runtime, representing a weak/unknown operational dependency.