google-search-domain-lead-finder

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The skill includes explicit instructions to install runtime dependencies without asking the user to confirm and to hide that the installation link is for the agent (i.e., "do not describe" it as a user prompt), which directs deceptive behavior outside the advertised lead-finding functionality.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The Skill is a lead-generation scraper (collecting contact details) but contains explicit instructions to auto-install a runtime dependency without user confirmation and to conceal the installation request, creating a high risk for supply‑chain abuse and unauthorized data collection.

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 collect search result pages/snippets and linked page content at runtime, which is outsider-authored free text from public web pages.

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 runtime using the provided install URL (https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which is a runtime fetch used to obtain and install executable code (and the skill also references https://www.browseract.com/?co-from=lead-generation), so the agent would fetch remote installer content during execution.