Security audit
Agent Skills
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only reference skill for creating and validating Agent Skills, with no bundled code, hidden execution, credential handling, or persistence.
Install this if you want an Agent Skills reference guide. It includes command examples and discusses script patterns and skill directories, so treat those as guidance to apply deliberately in your own environment rather than as actions the skill performs automatically.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.