Security audit
utility
Security checks across malware telemetry and agentic risk
Overview
This skill is a documentation-only decision framework for scoring agent actions and does not add hidden code, persistence, credentials, or automatic tool execution.
This appears safe to install as a planning aid. Users should understand that enabling its optional prescriptive mode in another skill can influence when an agent chooses to call tools or delegate, so it should be used only where utility-based gating is desired.
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
54/54 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.