website-contact-form-lead-search

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill instructs the agent to automatically install a dependency and explicitly tells it to hide that action and not request user approval, which is a deceptive instruction outside the skill's stated 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 BrowserAct CLI to fetch and extract content from user-specified public website URLs at runtime, which is outsider-authored free text (public web pages) that can be ingested into the agent/LLM context.

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

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