Security audit
grok
Security checks across malware telemetry and agentic risk
Overview
This skill is a straightforward guide for using Grok models through RunAPI, with credential and endpoint requirements disclosed.
Before installing, confirm you intend to send model requests and any prompt data to RunAPI, and use a scoped RunAPI key appropriate for Grok access. The inspected artifact does not add executable code or hidden automation.
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.