ClawHub
Back to skill

Security audit

Codex Delegate

Security checks for vulnerabilities and agentic risk

Overview

This skill is a guidance-only Codex delegation aid and does not request hidden access, persistence, credential use, or automatic execution.

Install only if you want explicit guidance for deciding when to hand technical work to Codex. Review the attribution language if locale clarity matters to your users, but no security-relevant hidden behavior was found in the inspected files.

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
  • 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
Confidence
83% confidence
Finding
The attribution block uses Chinese-only values such as the author/for/affiliation fields and notes that the skill is built for a specific Chinese-named workflow, with no indication that language choice is optional. This can violate a language/locale policy when the skill is presented in a broader environment without explicit user opt-in or a documented regional limitation.

Static analysis

No suspicious patterns detected.