AI Agent Security Audit
Security checks across malware telemetry and agentic risk
Overview
This is a security-audit skill that openly asks to inspect agent configs, installed skills, credentials, and runtime behavior for audit reporting.
Install only if you want an agent to perform security review tasks. When using it, scope scans to the intended agent config, skill directory, or workspace, and treat generated reports as sensitive because they may include file paths, credential findings, and runtime behavior details.
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.