Back to skill

Security audit

Writing Style Zhengliu

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese writing-style skill that restructures long text into a dense four-part summary and does not show unsafe system access or hidden behavior.

Install this if you want a strongly opinionated Chinese distillation-writing workflow. Be aware that it will push outputs into a strict four-section format and may invoke infographic-related tools when available, but the inspected artifact does not request sensitive access or hidden execution.

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 manifest description and the full markdown guidance require Chinese comprehension and implicitly force a specific language/locale for use. The file does not provide an opt-in, alternative language, or a documented reason that this skill must be Chinese-only.

Content

No source excerpt is available for this finding.