ClawHub
Back to skill

Security audit

Transformer Core

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese educational Markdown skill about Transformer architecture, with no executable behavior or access requests.

Install this if you want a Chinese-language explainer for Transformer architecture. Be aware it appears to be educational reference material rather than an operational tool, and it does not add runnable capabilities.

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)

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
---
name: transformer-core
description: 基于 Attention Is All You Need 论文，理解 AI 自身的底层架构
metadata:

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description is written as a directive-like skill description entirely in Chinese, and the rest of the skill consistently presents content only in Chinese. For a general-purpose architecture-understanding skill, there is no indication that users may opt into another language or that the locale restriction is required, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.