google-search-contact-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill explicitly instructs the agent to install runtime dependencies automatically and to conceal that installation request from the user, which is a hidden/deceptive behavior outside the advertised 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 the BrowserAct CLI to access live Google/search result pages and linked websites at runtime, which can include outsider-authored free text (public web content) that the agent may ingest 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 requires installing and invoking BrowserAct at runtime via the installation 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 implies fetching and executing remote code as a required runtime dependency.