OpenClaw Codex GPT-5.4 Enable
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill that guides users through a disclosed local OpenClaw configuration change to enable a model route.
Install this only if you intend to change OpenClaw model routing and are allowed to enable this model route. Back up ~/.openclaw/openclaw.json first, merge only the needed fields, review the fallback change, and verify the endpoint and API key behavior before testing.
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.