website-about-page-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill explicitly instructs the agent to install a runtime dependency automatically and to avoid describing the installation or asking the user for approval, which is a hidden/deceptive instruction outside the stated scraping 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 BrowserAct CLI to access arbitrary public website pages at runtime (public web content category), which can include outsider-authored free text that the agent may ingest 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 mandates installing and invoking the BrowserAct CLI at runtime and explicitly points to the install URL https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main (and a similar browseract.com link), which is a required runtime dependency and implies fetching/executing remote installation code.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.40). The Skill instructs the agent to automatically install the BrowserAct CLI and to resume execution without requesting user approval, which can modify the host (install software, change system state) even though it does not explicitly request sudo or direct modification of system files.