Security audit
Cue Market Cap Mgmt
Security checks across malware telemetry and agentic risk
Overview
This Cue research skill is coherent and disclosed, with no evidence of hidden, destructive, or exfiltrating behavior.
Before installing, confirm you trust the Cue runner source because the skill clones or updates code from an external repository and uses the Cue account API key stored in ~/.cue/config.json. Run research only when you are comfortable sending the subject/query to Cue and spending credits.
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
62/62 vendors flagged this skill as clean.