ClawHub
Back to skill

Security audit

education-learning-aggregation

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese education-skill routing README with broad triggers, but it contains no code, persistence, credential handling, or hidden behavior.

Install this if you want a Chinese-language education skill router. Review the trigger terms if you prefer narrower activation, especially in workspaces with many education-related skills installed.

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
  • 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 (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger policy uses very broad keywords such as '教育', '学习', '学科', '考试', and '作业', which are common in ordinary conversations and can cause this aggregation skill to activate outside the user's intended context. Because this skill routes into many sub-skills, over-triggering increases the chance of unnecessary data exposure, incorrect tool selection, or unintended execution paths across the aggregated skill set.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill content is written entirely in Chinese and the trigger guidance assumes Chinese-language keywords, with no indication that users can opt into another language or that language behavior is configurable. This can create user-consent and usability issues by forcing a language-specific interaction model, potentially confusing users or causing the skill to activate and respond in a language they did not request.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.