google-maps-phone-extractor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill contains deceptive runtime instructions that require installing dependencies automatically without user confirmation and explicitly tell the agent not to present the installation as a user-facing request, which is outside the advertised extractor purpose and hides important consent details.

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 access live Google Maps pages and extract visible listing text (outsider-authored free text from public web content), which would be ingested into the LLM context during execution.

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 and invoke the BrowserAct CLI at runtime using the installer link https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main (and references https://www.browseract.com/?co-from=lead-generation), which is a runtime fetch that would execute remote installation code and is treated as a required dependency.