tiktok-following-list-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The Skill instructs the agent to install dependencies and explicitly to do so without asking the user or describing the installation as a user-initiated browser request, which is a hidden/deceptive instruction to conceal actions outside the user's consent and the Skill's advertised data-collection purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The Skill explicitly instructs automatic installation of an external dependency without user consent and tells the agent not to request approval or disclose the install request, creating a high-risk supply-chain/remote-execution/backdoor vector even if the scraping behavior itself targets visible data.

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 invoke the BrowserAct CLI to access live TikTok pages at runtime (public/outsider-authored web content), which can be ingested as readable text into the LLM context via the BrowserAct workflow.

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

• Potentially malicious external URL detected (high risk: 0.90). The Skill requires installing and invoking the BrowserAct CLI at runtime via the links https://www.browseract.com/?co-from=social-media and https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main, which would fetch and install remote code that the agent would execute to run the Skill.