ClawHub
Back to skill

Security audit

voc

Security checks for vulnerabilities and agentic risk

Overview

This is a simple vocabulary-learning namespace skill whose scripts only print placeholder information, though its broad auto-routing language may surprise users.

Installing this skill should be low risk based on the current artifacts. Be aware that its instructions encourage broad routing for vocabulary-related requests, so users who want tighter control should invoke it explicitly or confirm before running its helper commands.

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

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the assistant to route on broad natural-language mentions like "voc" or generic requests about vocabulary learning, decks, or stats. This can cause unintended invocation when a user is merely discussing those topics, leading to surprise execution of a skill that has exec permission and reducing the user's control over when tools are run.

Natural-Language Policy Violations

Low
Confidence
77% confidence
Finding
The description says the skill is designed for learners wanting support across multiple language-learning functions, but it does not define clear user consent or locale-selection boundaries before routing vocabulary-related requests. In practice this can bias the assistant toward invoking the skill for language-related queries without explicit user choice, which may be confusing or inappropriate in multilingual contexts.

Static analysis

No suspicious patterns detected.