ClawHub
Back to skill

Security audit

Quality Training Planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language quality training plan generator with disclosed local document-output behavior and no evidence of hidden, persistent, or destructive actions.

Before installing, note that the skill is designed primarily for Chinese output and appears to be incomplete as packaged because referenced templates/scripts are absent. Use it for draft training plans, and review quality-standard references and any company-specific details before relying on the result.

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
80% confidence
Finding
The TRACE self-assessment explicitly highlights '完整中文', which indicates the skill is expected to operate fully in Chinese. Because the file does not offer an explicit language or locale choice anywhere else, this can be read as forcing a specific language without user opt-in.

Static analysis

No suspicious patterns detected.