yelp-business-review-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill explicitly instructs the agent to auto-install the BrowserAct dependency "without asking the user to confirm" and to hide that this is a request for the user to open their browser, which are deceptive, permission-bypassing instructions outside the scraper's stated data-collection 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 runtime browser-act Skill to “capture browser-visible page content” from user-specified Yelp/public URLs, which can include outsider-authored free text (review bodies, reviewer names, seller responses) that the LLM ingests during scraping.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly directs the agent at runtime to install and invoke the BrowserAct CLI using the installer links 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 causes the agent to fetch and execute remote installer code as a required dependency.