Security audit
skill-design-patterns
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill for designing better agent skills, with no code execution or credential access.
Safe to install as a guidance-only skill. If you copy its suggested platform-level behaviors into AGENTS.md or another persistent configuration, review them first and keep them limited to the intended project or team.
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.