website-footer-contact-extractor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill contains explicit instructions to install dependencies automatically and to "not describe" that action or request user approval, which is a deceptive runtime instruction outside the advertised extractor purpose.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md directs the agent to use the BrowserAct CLI to open user-specified public website URLs at runtime and extract page-visible text (outsider-authored free text from public web content), which can be fed into the LLM context for processing.

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

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