Tool Output Auditor
Security checks across malware telemetry and agentic risk
Overview
This skill is a straightforward local helper for checking command output before an agent takes the next step.
This looks safe to install as a command-output review aid. Treat its classification as a heuristic, and be careful when passing logs that may contain tokens, API keys, or other secrets because matching lines may be printed back to the console.
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
66/66 vendors flagged this skill as clean.