google-maps-restaurant-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill contains explicit instructions to install dependencies without user confirmation and to conceal that installation requests require the user's browser (i.e., "do not describe it as a request..."), which are deceptive directives altering agent transparency and consent beyond normal scraping behavior.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The Skill contains explicit instructions to automatically install external tooling without user consent and to scrape contact data (emails/phones), creating a high risk of unauthorized installation, supply-chain abuse, and covert data exfiltration.

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 invoke the browser-act Skill for live browser execution to access Google Maps pages at runtime, which can ingest outsider-authored free text from public web content into the LLM context via the browser-extracted page content.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to install and invoke BrowserAct using the URLs https://www.browseract.com/?co-from=lead-generation and https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main, which are required runtime dependencies that can fetch and install remote code that controls agent execution.