Security audit
QMS环境因素技能
Security checks across malware telemetry and agentic risk
Overview
This skill is a local QMS analysis helper that reads user-provided JSON and generates charts or a PDF report, with no hidden network, credential, or persistence behavior found.
Before installing, confirm you are comfortable providing the skill any organization-specific QMS, risk, or business context included in your JSON file. Generated reports may contain sensitive internal analysis, so choose the output location deliberately and review the PDF before sharing it.
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.