made-in-china-supplier-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The Skill includes deceptive runtime instructions that tell the agent to install BrowserAct automatically and to hide or misrepresent that installation to the user (e.g., "without asking the user to confirm" and "Do not describe it as a request..."), which overrides user consent and is outside the advertised 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 the BrowserAct CLI to access real Made-in-China web pages at runtime and “capture browser-visible page content” (public web content is outsider-authored free text that can be ingested into the LLM context via the browser-act workflow).

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 to automatically install and invoke the BrowserAct CLI at runtime via the link(s) https://www.browseract.com/?co-from=ecommerce and https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main, which implies fetching and executing external code as a required runtime dependency.