google-maps-franchise-lead-search

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill instructs the agent to install BrowserAct dependencies automatically without user confirmation and explicitly to conceal that action ("Do not describe it...do not request separate approval"), which is a deceptive instruction unrelated to the stated lead-search 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 access and interact with live Google Maps/public web pages, which can cause outsider-authored free text from those pages/listings to be ingested into the LLM context for extraction.

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 to automatically install and invoke the BrowserAct runtime at request time by fetching from https://www.browseract.com/?co-from=lead-generation (and the install redirect URL https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which implies retrieving and executing remote installer code as a required runtime dependency.