Security audit
Call Grok4 Llm
Security checks across malware telemetry and agentic risk
Overview
This skill does not run code or access data, but its instructions do not match its Grok4-calling description and could redirect the assistant into a creative-meeting persona.
Review before installing. The main risk is behavioral rather than technical: invoking this skill may make the assistant follow a creative-meeting prompt instead of helping call Grok4. It does not appear to request secrets, run commands, or transmit data.
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.