Ai Spend Audit
Security checks across malware telemetry and agentic risk
Overview
This skill appears to be a benign AI-spend-audit guide with no evidence of hidden execution, persistence, credential use, or data exfiltration.
Install only if you are comfortable sharing the AI billing and usage details needed for an audit with your agent. Review any external vendor links before using them, and avoid providing credentials unless a later workflow explicitly requires them and you trust the destination.
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
63/63 vendors flagged this skill as clean.