Security audit
thinking-bounded-rationality
Security checks across malware telemetry and agentic risk
Overview
This is a small decision-making guidance skill with no code execution, data access, persistence, or hidden behavior.
This skill is reasonable to install if you want agents to avoid over-searching on reversible, low-stakes choices. Do not apply it to security reviews, tests, migrations, data-loss risks, or other decisions where getting the right answer matters more than stopping early.
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.