Security audit
agent-expenditure
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill for reviewing agent token waste, with no executable code or hidden high-impact behavior found.
This skill appears safe to install as a review aid. It may refer to agent logs or token-history comparisons, so use it with bounded, intentional workflow data rather than broad private logs unless that is what you intend to analyze.
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.