ClawHub
Back to skill

Security audit

快速翻译

Security checks for vulnerabilities and agentic risk

Overview

This is a simple translation instruction skill with no executable components; the main caution is that its claimed translation history is not explained.

Safe to install for normal translation use. Avoid submitting confidential, legal, medical, or business-sensitive text unless you are comfortable with the unspecified translation history behavior.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly advertises a translation history feature, which implies user-submitted text may be stored, but it provides no disclosure, retention details, or warning about submitting sensitive content. Because translation inputs may contain personal, confidential, legal, medical, or business data, this omission creates a meaningful privacy risk through unexpected data retention.

Natural-Language Policy Violations

Low
Confidence
73% confidence
Finding
The natural-language instructions, examples, and output format are entirely presented in Chinese, which can amount to a language/locale constraint if the skill expects users to interact that way. The file does not state that other instruction languages are accepted or provide any user choice on interface language.

Static analysis

No suspicious patterns detected.