ClawHub
Back to skill

Security audit

Openclaw Codex Collaboration

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language workflow guide for using Codex through OpenClaw, with expected repository write authority and run logging but no hidden persistence or exfiltration behavior.

Install this only if you want a Chinese-language OpenClaw/Codex collaboration workflow. Review the target repository, task prompt, and allowed scope before running the workspace-write command, because it is designed to let Codex modify files in the selected repo and write local execution records.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest description and the full skill instructions are written entirely in Chinese and specify the collaboration规范 in that language, with no indication that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

bash
# 开发任务（默认）
codex -a never exec -C "$REPO" -s workspace-write --json -o "$RESULT_FILE" "$PROMPT"

# 只读分析
codex -a never exec -C "$REPO" -s read-only --json -o "$RESULT_FILE" "$PROMPT"

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

bash
# 开发任务(默认)
codex -a never exec -C "$REPO" -s workspace-write --json -o "$RESULT_FILE" "$PROMPT"

# 只读分析
codex -a never exec -C "$REPO" -s read-only --json -o "$RESULT_FILE" "$PROMPT"

Static analysis

No suspicious patterns detected.