Back to skill

Security audit

AI协作写作方法论

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language writing workflow skill with no code, persistence, hidden data access, or privileged actions.

Installers should treat this as a guidance-only writing skill. Be aware it is written for Chinese-language material drafting and may route broad Chinese requests about writing with AI, but it does not perform actions on its own.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The entire skill is written in Chinese and implicitly targets Chinese-language interaction without stating language constraints or requiring user opt-in. In multilingual environments this can lead to inappropriate activation, degraded user experience, or unexpected language switching, which is a scope/control issue even if it is not directly a code-execution risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger phrases are very broad and map to common user requests about writing with AI, which can cause this skill to activate in situations where the user did not specifically ask for this methodology. Over-broad invocation increases the chance of unintended routing, response hijacking, or suppression of more appropriate skills, especially in general writing-assistance contexts.

Content

No source excerpt is available for this finding.