ClawHub
Back to skill

Security audit

editor-adversarial-reviewer

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language script review checklist with an isolated reviewer workflow and no evidence of hidden access, persistence, or data exfiltration.

Install this only if a Chinese-language adversarial script-review workflow is intended. Be aware that it sends the provided script content into an isolated subagent for critique and may produce strict rejection recommendations, but it does not appear to modify files or access sensitive local data.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill is entirely written in Chinese and does not provide a language choice, fallback, or documented justification for restricting usage to Chinese-speaking users. This can cause users or downstream agents to misunderstand operational constraints and review criteria, which may lead to incorrect execution of the skill or bypass of expected review behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.