Security audit
One Pager
Security checks across malware telemetry and agentic risk
Overview
The skill appears to be a single documentation-only skill with clean scanner telemetry and no evidence of hidden code, persistence, or data access.
Before installing, read the SKILL.md because the raw instructions are what shape agent behavior. Based on the supplied evidence, this version does not show code execution, persistence, credential handling, or hidden data flows, but it should still be used with normal caution for any skill that influences agent reasoning.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.