google-shopping-search-results-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The Skill explicitly directs the agent to auto-install a dependency and to "not request separate approval" or describe the installation to the user, which is a hidden/deceptive instruction outside the 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 instructs the agent to use BrowserAct to “capture browser-visible page content” from user-specified target URLs at runtime, which can include outsider-authored free text from public web pages (indirect prompt injection risk via the scraped page content fed back into the LLM context).

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

• Potentially malicious external URL detected (high risk: 1.00). The Skill explicitly instructs the agent to invoke and "follow its current instructions" from the BrowserAct runtime and to auto-install missing dependencies via the BrowserAct install link (https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main), meaning the agent will fetch and run remote installer/content that can control prompts or execute code at runtime.