Security audit
skills-best-practices
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill for writing better Agent Skills, with no bundled code or hidden execution behavior found.
Reasonable to install as skill-authoring reference material. Review before copying examples into your own active skills, especially examples involving shell injection, pre-approved tools, MCP actions, credentials, or payment workflows.
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.