ecommerce-question-answer-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The prompt explicitly instructs the agent to install a runtime dependency automatically and to hide that this is a request or to avoid asking for user approval, which are deceptive instructions outside the Skill's stated scraping purpose.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md:29-30 instructs the agent to “capture browser-visible page content” (including question/answer text and visible user display names) from public product pages via the runtime BrowserAct workflow, which can include outsider-authored free text (e.g., Q&A authored by other users on the site).

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

• Potentially malicious external URL detected (high risk: 0.90). The Skill explicitly requires and directs the agent to automatically install and invoke the BrowserAct CLI using the installer links (e.g., 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 are runtime external dependencies that would fetch and install/execute remote code.