tiktok-profile-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). Yes — the skill contains explicit, deceptive instructions to install dependencies without asking the user and to conceal that action (e.g., "do not describe it as a request..."), which overrides normal consent and falls outside the stated scraping purpose.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to use the runtime browser-act Skill to access live TikTok/public pages based on user-supplied target URLs/queries, which can cause outsider-authored free text from those fetched web pages to be ingested into the LLM context via the BrowserAct execution path.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires the BrowserAct CLI as a runtime dependency and instructs the agent to automatically install it using the link https://www.browseract.com/?co-from=lead-generation (and a redirect variant), which indicates fetching and executing remote installer code at runtime.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.40). The skill instructs the agent to automatically install the BrowserAct CLI and resume execution without asking the user for confirmation, which encourages the agent to modify the host system by installing software (even though it does not explicitly request sudo, create users, or edit system files).