Security audit
Hanlon's Razor
Security checks across malware telemetry and agentic risk
Overview
This is a text-only reasoning skill that helps users avoid assuming bad intent and does not request access to files, credentials, tools, or persistent background behavior.
Installers should understand this is a reasoning aid, not a safety or abuse-risk assessment tool. It is appropriate for everyday conflict interpretation, but users should avoid applying it where there is documented malice, a serious power imbalance, abuse risk, or high consequences from underestimating intent.
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
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.