tiktok-comment-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The skill includes explicit, deceptive instructions to install dependencies automatically and to avoid telling or asking the user for approval (i.e., “do not describe…do not request separate approval”), which instructs the agent to hide actions outside the skill’s stated data-scraping purpose.

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

• Third-party content exposure detected (high risk: 0.75). The required workflow invokes the browser-act Skill to access live TikTok/public web pages at runtime, which can cause outsider-authored free text from arbitrary fetched pages (e.g., comments/profile content) to be ingested into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill treats the BrowserAct CLI/Skill as a required runtime dependency and instructs the agent to automatically install it using the installer URL https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main, which is used at runtime to fetch/install external code.