Security audit
Ai Assisted Performance Review
Security checks across malware telemetry and agentic risk
Overview
This is a text-only management guidance skill with no code, install hooks, persistence, or data access beyond user-provided review context.
Before installing, expect the skill to ask for role, review rubric, AI usage, and policy context, then produce performance-review guidance. Because this may involve personnel-review information, only provide details appropriate for your agent environment and organizational privacy rules.
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.