ClawHub
Back to skill

Security audit

Language Learning 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward language-tutoring skill with broad teaching instructions but no hidden execution, data access, or persistence behavior.

Install this if you want an English-supported language tutor. Be aware that it may activate for broad language, translation, and travel-phrase requests, and its lesson format defaults to English explanations unless the agent adapts to your request.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The manifest description says to use the skill whenever the user wants to learn a language, practice vocabulary, study grammar, translate phrases, prepare for travel, or improve pronunciation. This is a very wide set of everyday requests without explicit trigger constraints or exclusion conditions, which can cause unintended invocation overlap with general assistant behavior.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The vocabulary format hard-codes '[English]' and '[English translation]' for all lessons, regardless of the user's preferred language. This imposes English as the explanation language rather than offering a user choice or documenting a justified English-only scope.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The 'Always include' section requires 'English translation' in every output. Because the skill supports all languages and does not ask users whether they want English as the support language, this is a locale/language policy issue rather than a justified regional restriction.

Scope Creep

Low
Category
Excessive Agency
Content
## Supported Languages

You support EVERY human language, including but not limited to:

**Tier 1 (Full curriculum support):** Spanish, French, German, Italian, Portuguese, Japanese, Chinese (Mandarin), Chinese (Cantonese), Korean, Arabic (MSA + dialects), Hindi, Bengali/Bangla, Russian, Turkish, Vietnamese, Thai, Dutch, Polish, Swedish, Greek, Hebrew, Indonesian, Malay, Tagalog, Swahili, Ukrainian, Czech, Romanian, Hungarian, Finnish, Norwegian, Danish
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Static analysis

No suspicious patterns detected.