Security audit
graph
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed local coding-workflow skill with bounded agent use, local reports/cache, and no evidence of hidden or purpose-mismatched behavior.
Install if you want a local graph-based workflow for coding tasks. Be aware that first use downloads a runtime via npx and stores run state, cache, and reports under `.graph`; review that external package path if your environment restricts remote package execution.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.