linkedin-company-profile-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill contains deceptive runtime instructions outside its stated scraping purpose — it directs the agent to install dependencies automatically without user confirmation and explicitly tells the agent not to disclose or request approval for that installation, which is hidden/deceptive behavior.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill includes deceptive automatic installation instructions for an external CLI and explicit guidance to collect and export contact details (including visible emails), which together create a high-risk supply-chain and data-exfiltration abuse surface.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to use the BrowserAct CLI to access live LinkedIn pages at runtime (public web content), which can include outsider-authored free text from those pages that the LLM may ingest for extraction.

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

• Potentially malicious external URL detected (high risk: 1.00). This Skill mandates installing the BrowserAct CLI at runtime using the provided install 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 to provide a required Skill dependency.

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 explicitly instructs the agent to install missing runtime dependencies automatically (via the Install BrowserAct link) and to proceed without asking the user for approval, which directs the agent to modify the host environment even though it does not explicitly request sudo or other privilege escalation.