Back to skill

Security audit

OpenClaw Codex GPT-5.4 Enable

Security checks for vulnerabilities and agentic risk

Overview

This documentation-only skill gives a scoped, reversible workflow for changing OpenClaw model configuration, with no hidden code or automatic actions found.

Before installing, confirm you understand the configuration change, back up ~/.openclaw/openclaw.json, and verify that adding openai-codex/gpt-5.4 as a provider, alias, and fallback is appropriate for your OpenClaw environment.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The file's user-facing instructions switch to Chinese starting at L017 and remain in that language throughout the operational guidance. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicit and justified, which is not present here.

Content

No source excerpt is available for this finding.