Security audit
Agent Introspection
Security checks across malware telemetry and agentic risk
Overview
This is a text-only self-reflection skill with no executable code, credentials, network use, or hidden install behavior.
Install this if you want a Chinese-oriented agent reflection aid. Keep any reflection notes in a known limited location, and make sure the agent still asks before taking irreversible, external, or high-impact actions during reflection.
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.