linkedin-sales-navigator-search-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill explicitly instructs the Agent to install dependencies automatically and to hide or avoid requesting user approval for that installation, which is a deceptive/hidden instruction outside the advertised scraping functionality.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The Skill contains explicit instructions to automatically download/install an external runtime without user confirmation and to scrape/export visible contact and contact-detail data, creating clear supply-chain and data-exfiltration risks and deliberate consent-evasion behavior.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required runtime workflow invokes the browser-act Skill to access live LinkedIn/public pages, which can cause outsider-authored free text from those fetched web pages to be ingested into the agent’s LLM context via BrowserAct’s page extraction.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires and instructs the agent to automatically install and invoke the BrowserAct CLI at runtime using the 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 would fetch and execute remote code and is a required runtime dependency.