ClawHub
Back to skill

Security audit

Grade English Homework (3-6)

Security checks for vulnerabilities and agentic risk

Overview

This is a simple educational grading prompt with no code, install behavior, persistence, or data access beyond the homework text the user provides.

Before installing, consider narrowing the trigger wording if you often ask for general English editing unrelated to children's homework. Otherwise, the skill is proportionate for its stated educational use and does not add local or remote access risks.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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

Medium
Confidence
95% confidence
Finding
The trigger list is broad enough that the skill may activate for generic phrases like 'check my English' or '改错' without clear homework or child-grade context. That can cause unintended routing of unrelated user requests into this skill, leading to mismatched instructions, incorrect assumptions about the user, and inappropriate handling of content.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
Mandating Chinese feedback without checking user preference can override the user's language choice and expose information in an unintended language context, especially if the requester is not the student or does not read Chinese. In this skill's educational setting the harm is limited, but it still creates a privacy, usability, and consent issue through inflexible output behavior.

Static analysis

No suspicious patterns detected.