Back to skill

Security audit

Zaregoto Miko Style

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only style rewriting skill with no code execution, credential access, persistence, or data movement.

Install this if you want Chinese Zaregoto/Miko-style rewriting. Be aware that broad trigger phrases may make it activate for generic character-voice or style-conversion prompts, so use explicit wording when you want another style or no persona transformation.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list is broad enough to match ordinary requests such as generic 'character voice' or 'style conversion', which can cause the skill to activate when the user did not specifically ask for this persona. That increases the chance of unintended style hijacking, user confusion, and interference with other more appropriate skills, even though the skill itself is not directly harmful.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all instructions and examples in Chinese only, and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking context. The policy for natural-language violations applies to all file types and specifically covers forcing a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The description frames the skill as always converting content into a specific fictional voice without indicating that this should happen only when the user clearly wants that transformation. In practice this can reduce user control and cause outputs to be forced into an unwanted persona or language style, but the surrounding context is limited to harmless stylistic rewriting, so the danger is relatively low.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.