ClawHub
Back to skill

Security audit

english-dict

Security checks for vulnerabilities and agentic risk

Overview

This is a small local English-to-Chinese dictionary helper with limited coverage, not a high-impact or hidden-behavior skill.

Install only if you want a lightweight Chinese-language vocabulary helper with a very small built-in word list. For broad or authoritative dictionary results, you would need to review and configure any external API changes yourself.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The skill description broadly represents a usable English-to-Chinese dictionary lookup tool, but the code only partially fulfills that purpose. It can produce Chinese definitions and two example sentences for a very small predefined set of words. For any other input, it does not actually perform a real dictionary lookup; instead it returns a fabricated phonetic string, a placeholder 'meaning' advising use of an external API, and two generic sentences. There are no undeclared risky behaviors or permission/resource mismatches, but the implemented capability is materially narrower than the declared purpose, so this is a description-behavior mismatch.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The description and body specify that English words are queried to get Chinese definitions, and the skill is presented in Chinese without offering any user choice of output language or locale. This creates a natural-language locale policy issue because the skill appears to mandate Chinese responses rather than allowing user preference.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding
Suspicious Unicode normalization or mixed-script content

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The module docstring describes the tool entirely in Chinese, and later user-facing messages are also presented only in Chinese. This imposes a specific language/locale on users without any opt-in or configuration, which matches the language-policy violation criteria.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The usage/help text shown to users is only in Chinese, and the formatted output throughout the script also uses Chinese labels and notices. Because the skill does not provide a language selection mechanism or explicit justified locale restriction, it violates the language/locale policy requirement.

Static analysis

No suspicious patterns detected.