ClawHub
Back to skill

Security audit

Table Specification

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only exam blueprint skill with no executable code, persistence, credential access, or hidden data flow.

Install this if you want a Chinese-oriented workflow for building vocational education exam blueprints. Be aware that it may activate for broad exam-creation requests and may not work as intended unless the missing referenced materials are supplied or the agent can proceed without them.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill declaration says it must be used for very broad prompts such as any generic request to 'help me create an exam' or 'design a test', which can override normal skill routing and capture common user intents too aggressively. This creates prompt-scope hijacking risk: the agent may invoke this skill in situations where the user did not ask for a blueprint/table, causing irrelevant workflow injection, unnecessary file reads, and reduced control over downstream behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill content is written to operate in Chinese and strongly frames outputs in that locale without indicating user choice, which can force a language/locale mismatch during invocation. While not a direct code-execution issue, it can degrade user comprehension, cause incorrect formatting or terminology assumptions, and override user preferences in multilingual contexts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.