Security audit
ia-simplifying-code
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent code-refactoring guide that asks the agent to make scoped, behavior-preserving code simplifications with verification.
Install this if you want stricter guidance for behavior-preserving refactors. Review the agent's proposed edits as usual, especially when it removes guards, dead code, or internal compatibility paths, but the skill itself does not show hidden or disproportionate 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.