Security audit
深度核查
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed Cue research helper for deep verification workflows, with expected network use and credit consumption controls.
Before installing, be aware that first use may clone or update Cue's runner code under ~/.cue, the runner will use your Cue login/API key, and deep research consumes Cue credits after you confirm. This is coherent with the skill's purpose, but you should only proceed if you trust the Cue runner source and are comfortable sending your research query to Cue.
SkillSpector
By NVIDIA
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
VirusTotal
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.