Security audit
Skill Publishing Team — Agent Configuration Bundle
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent multi-role workflow for creating, testing, documenting, reviewing, and preparing skill packages for release.
Install only if you want a multi-agent workflow that can edit files, run shell commands for testing and release checks, and store/reuse task context while working on skill packages. Review generated changes before publishing anything publicly.
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
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.