tiktok-shop-category-ranking-scraper

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

• Third-party content exposure detected (low risk: 0.10). The agent navigates arbitrary web pages and marketplace listings via BrowserAct, which falls under low risk as the agent must actively search or fetch specific outsider-authored content.

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 an unofficial GitHub repository (https://github.com/browser-act/skills/tree/main) via a redirect link during runtime if missing, representing a weak/unknown operational dependency.