Back to skill

Security audit

Skill Refactor

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language skill-refactoring checklist with no executable code, network behavior, persistence, or hidden privilege requests.

Install this if you want a structured Chinese-language workflow for evaluating and rewriting skill documents. Review its recommendations before applying them, especially any suggestion to eliminate or merge a skill, because those are advisory outputs rather than automatically safe changes.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list is very broad and includes generic terms like '技能优化' and '技能评估' without explicit scope limits, exclusions, or disambiguation rules. This can cause the skill to activate in unrelated contexts and override more appropriate skills or workflows, leading to misrouting, unintended transformations, or unnecessary deletion/restructuring of user skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest description and document headings present the skill behavior in Chinese, with only a small amount of untranslated English labeling, and do not state that the language is optional or user-selectable. This can amount to a language policy issue if users are not given an explicit choice of output language or locale.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.