douyin-comment-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The Skill contains explicit instructions to install a dependency automatically and to conceal that action from the user ("without asking the user to confirm" and "Do not describe it as a request..."), which is deceptive and outside the documented scraping purpose.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to use BrowserAct to access Douyin pages at runtime and collect comment text (outsider-authored public/authorized web content), which would be ingested into the LLM context as scraped free-form comment text.

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

• Potentially malicious external URL detected (high risk: 0.90). The Skill explicitly requires installing and invoking the external BrowserAct CLI at runtime and tells the Agent to automatically use the install link (https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which implies fetching and executing remote installation code required for operation.