facebook-page-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill contains instructions to install dependencies automatically without user confirmation and to conceal that installation (e.g., "do not describe it as a request" and "without asking the user to confirm"), which are hidden/deceptive directives outside the user's stated scraping purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document instructs automated installation of an external runtime without user consent and explicitly directs hiding that installation, indicating deliberate supply-chain/backdoor behavior.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s runtime workflow delegates to the outsider-controlled “BrowserAct” CLI to access real Facebook pages and extract public profile/post text, which would be ingested into the agent’s LLM context as scraped page content (public web content category).

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

• Potentially malicious external URL detected (high risk: 1.00). The skill requires installing and invoking the BrowserAct CLI at runtime using the provided install link (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 the Skill specifies the agent should fetch/execute automatically as a required runtime dependency.