tiktok-creative-center-intent-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The Skill explicitly directs automatic installation of BrowserAct without user confirmation and tells the agent not to describe the installation as a request or ask separate approval, which is a deceptive instruction to hide actions from the user and falls outside normal, transparent behavior.

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 invoke the browser-act Skill to access live public TikTok pages at runtime, which can ingest outsider-authored free text from fetched web content into the LLM context via the browser-extracted page content.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent at runtime to install and invoke the BrowserAct CLI using the URL https://www.browseract.com/?co-from=lead-generation (and the redirected installer URL https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which is a required runtime installation step that would fetch and execute external code.