Security audit
Operon Guard
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent wrapper for an external agent-testing CLI, with its main execution risks disclosed in the documentation.
Install only if you are comfortable trusting the external `operon-guard` package source. When using it, do not run it against unreviewed third-party Python agents on your main machine, because the documented import behavior can execute target-file top-level code; use a sandbox and treat the score as one input alongside source review and least-privilege permissions.
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.