write-skills-demo
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill for writing and testing agent skills, with no executable code or hidden data access.
Install this if you want help creating or testing agent skills. Review any generated SKILL.md or CLAUDE.md content before making it persistent, keep test scenarios synthetic, and avoid putting secrets or private data into examples.
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.