Security audit
escalation-governance
Security checks across malware telemetry and agentic risk
Overview
This skill is a governance guide for model escalation and does not request sensitive access or perform actions by itself.
Before installing, understand that this skill changes agent guidance around when to use stronger or higher-effort models, which may affect cost and latency, but the inspected artifact does not itself access data or run code.
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.