Security audit
人物核查
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed Cue research workflow for person checks, with expected external API use, local runner setup, API-key use, and credit consumption clearly called out.
Before installing, understand that the skill may clone/update a third-party runner, read your local Cue API key, send the queried person or organization details to Cue, and spend Cue credits after confirmation. Use it only for appropriate public-record due diligence and verify important conclusions independently.
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Static analysis
No suspicious patterns detected.