linkedin-company-employee-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill contains explicit instructions to install a runtime dependency automatically and to conceal that installation from the user ("without asking the user to confirm" and "Do not describe it as a request..."), which are hidden/deceptive directives outside the advertised scraping purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The document contains instructions that deliberately direct automatic installation of an external runtime dependency without user consent and explicitly instructs the agent to hide that installation request, which is indicative of a supply-chain/backdoor risk and potential for covert data-exfiltration enablement.

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 and execute tasks on live LinkedIn pages at runtime, which can ingest outsider-authored free text from those public web pages into the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The Skill explicitly requires installing the BrowserAct CLI at runtime and instructs automatic installation via the provided links (https://www.browseract.com/?co-from=social-media and https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which would fetch and install remote code as a required runtime dependency.