ClawHub
Back to skill

Security audit

Codex Profiler

Security checks across malware telemetry and agentic risk

Overview

This skill fits Codex profile management, but it handles OAuth tokens and local gateway/auth-store changes in a way that needs careful review before installing.

Install only if you are comfortable giving this skill access to your local OpenClaw Codex OAuth profiles and allowing it to queue auth-store changes and restart the local gateway. Prefer the documented gateway-native openclaw models auth commands for mutations where possible, avoid using it on shared machines, and check /tmp/openclaw after use for leftover token-bearing payload or staged auth files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The script writes live OAuth access and refresh tokens to predictable files under /tmp/openclaw, including a payload file later consumed by the apply step. Temporary directories are a high-risk location for sensitive credentials because other local processes/users may read, race, or retain them longer than intended, especially when no explicit permission hardening or cleanup is performed.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.