Security audit
thinking-map-territory
Security checks across malware telemetry and agentic risk
Overview
This skill is a small reasoning checklist that tells the agent to verify real code or data when claims conflict, without requesting sensitive access or adding persistence.
This skill is reasonable to install if you want the agent to verify claims against actual code or data before deciding. As with any verification-oriented skill, expect it may suggest reading files or running checks that are relevant to the task, but this artifact does not add hidden automation or privileged behavior.
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.