Back to skill

Security audit

mayu-cn

Security checks for vulnerabilities and agentic risk

Overview

This skill is not malicious, but it installs a high-priority always-on behavior protocol that can shape unrelated assistant conversations.

Install this only if you intentionally want a Chinese-language, always-on AI self-reflection protocol to influence general assistant behavior. Prefer an on-demand configuration using /mayu, narrower triggers, or lower priority if you do not want it affecting unrelated tasks.

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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The description and nearly all user-facing content are presented only in Chinese, while the file does not state that the skill is region-specific or that users may choose another language. This can constitute a language policy issue when a skill implicitly enforces one language without opt-in or justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger set includes broad terms such as “AI行为”, “自省”, and “思想实验”, which are likely to appear in ordinary conversations unrelated to this skill. Because the skill is also configured for high-priority/global activation elsewhere, these broad triggers can cause unintended invocation and prompt-context takeover, altering assistant behavior when the user did not explicitly request this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is marked global, priority = 9, and always_on = true, but it does not define clear boundaries for when it should yield to other instructions or remain inactive. In practice, this creates persistent behavioral override risk: the skill’s long normative prompt can continuously shape responses across unrelated tasks, increasing the blast radius of accidental activation and making prompt-governance conflicts more likely.

Content

No source excerpt is available for this finding.