Security audit
Deep modules for agent-native codebases
Security checks across malware telemetry and agentic risk
Overview
This is a coherent code-refactoring skill that may inspect and modify a repository, but the reviewed evidence does not show deception, exfiltration, persistence, or destructive behavior.
Install only if you are comfortable giving the agent repository read/write access for refactoring. Use a branch, review scaffolded files and move plans before committing, and do not let the agent run local scripts from an untrusted repository without inspection.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.