ClawHub
Back to skill

Security audit

Pinyin Converter

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local Pinyin conversion skill; its main issue is limited accuracy/coverage, not unsafe behavior.

Safe to install as a lightweight local utility, but do not rely on it as a complete Chinese-to-Pinyin converter: it only covers a small embedded character set and may silently omit unsupported Chinese characters or whitespace.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The code’s primary purpose does align with Chinese-to-Pinyin conversion, and it does implement tone-preserving output, tone removal, and an initials mode. However, the declared description overstates the capability. The implementation is not a general Chinese-to-Pinyin converter; it only handles a limited embedded character map and silently omits unsupported Chinese characters and whitespace. Also, '首字母大写' typically suggests capitalization formatting, but the code’s --initial mode outputs only the first letter of each syllable rather than full Pinyin with capitalized initials. There are no hidden permissions, unrelated triggers, or suspicious undeclared behaviors, but the functional scope is materially narrower than described.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The script emits mode labels in Chinese string literals ("首字母", "无声音调", "标准拼音") regardless of user preference. This is a natural-language locale choice embedded in code, and there is no opt-in or documented justification that the skill is intentionally Chinese-only.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.