Security audit
Map Is Not the Territory
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only coaching skill about checking whether metrics and plans still match reality, with no executable behavior or sensitive access.
This skill appears safe to install as a reasoning aid. It may influence how an agent frames decisions about metrics, models, and plans, so users should treat its outputs as analytical coaching rather than factual proof and verify cited examples or business conclusions where stakes are high.
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.