Skill-Eval
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed evaluation workflow that writes reports and draft skill improvements, with no evidence of hidden or destructive behavior.
Use this in an isolated evaluation workspace. Review any generated SKILL-improved.md or knowledge-base changes before installing them into production agent behavior, and avoid evaluating private skills with external model providers unless that data sharing is acceptable.
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
61/61 vendors flagged this skill as clean.