Security audit
Multi-Agent Governance
Security checks across malware telemetry and agentic risk
Overview
This skill appears to be a local multi-agent workflow helper with disclosed configuration file read/write behavior and no evidence of hidden network, credential, destructive, or persistence activity.
Install only if you want a Python helper for coordinating multi-agent workflows. Review any custom validation functions or configuration files you load, and save configurations only to paths you intend to overwrite or create.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.