google-maps-reviewer-contact-search

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The Skill explicitly instructs the agent to install runtime dependencies automatically and to conceal that action from the user ("without asking the user to confirm" and "Do not describe it ... do not request separate approval"), which are deceptive instructions outside the user's expected consent model for the Skill.

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 and interact with live public Google Maps pages at runtime, which can cause outsider-authored free text (e.g., listing content like phone/email/website snippets) to be ingested into the LLM context via the browser-extracted page text.

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 from the external installer URL (https://www.browseract.com/?co-from=lead-generation and its redirect to GitHub: https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which is a required runtime dependency that would fetch and execute remote code.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). This skill instructs the agent to automatically install a runtime dependency (BrowserAct CLI) without user confirmation, which directs the agent to modify the host system state and autonomously perform software installation.