ClawHub
Back to skill

Security audit

README Translator

Security checks for vulnerabilities and agentic risk

Overview

This skill appears non-destructive, but it does not actually perform the README translation behavior it advertises.

Review this before installing if you expect a working translator. It does not show malicious behavior, but users may be misled into relying on a placeholder script that ignores the README content and requested output.

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 (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

There is a clear description-behavior mismatch. The declared purpose is an automatic README translator supporting multiple languages. In reality, the code only prints a canned markdown stub with placeholder text indicating where translated content would go. Although it accepts a language parameter and names an output file variable, it neither uses the input README nor writes translated content based on the selected language. The primary purpose described is not implemented by the supplied code.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description is written as "自动翻译 README 文件" (automatically translate README files), which indicates a translation behavior but does not offer any user choice of target language or justify a fixed locale. For a translation skill, imposing a language/locale implicitly without opt-in can violate the language-choice policy described in SQP-3.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script sets the default target language to zh and emits Chinese-language content in the generated README without first offering a language choice or requiring explicit opt-in. This is a natural-language locale policy concern because it forces a specific language by default rather than preserving user choice.

Content

No source excerpt is available for this finding.