naver-shopping-search-results-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill instructs the agent to install dependencies automatically and explicitly tells the agent not to ask the user or describe the action as a user-facing request, which is a deceptive, hidden instruction outside the scraping task's stated 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 “capture browser-visible page content” and “invoke the browser-act Skill” on user-supplied target URLs at runtime, which can include outsider-authored free text from public web pages fetched by BrowserAct.

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 a required runtime dependency from the external installer URL which would fetch and execute remote code at runtime: https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main