Back to skill

Security audit

测试2123

Security checks for vulnerabilities and agentic risk

Overview

This is a brainstorming/planning skill with disclosed project inspection and design-document output, and I found no hidden execution, exfiltration, or privilege behavior.

Install this if you want a structured brainstorming workflow that may inspect your current project and, after validation, create and commit a design document. Non-Chinese readers should review a translation first so they understand the workflow.

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
  • 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
96% confidence
Finding

The skill's name and purpose are described entirely in Chinese, and all operational instructions are written only in Chinese. This creates a language/locale constraint without any opt-in or explanation that the skill is region-specific, which matches the policy category for forced language use.

Content

No source excerpt is available for this finding.