website-demo-request-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 automatically without user confirmation and to hide that installation/request from the user, which are deceptive instructions outside the advertised lead-search purpose.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). This skill’s required workflow invokes the browser-act Skill to fetch and extract content from user-specified public website pages at runtime (outsider-authored free text from arbitrary URLs/pages becomes LLM-readable context via the browser extraction step).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill requires installing the BrowserAct CLI at runtime using the provided install link (https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which would fetch and execute remote installer code as a required dependency.