ClawHub
Back to skill

Security audit

Language Learning Tutor

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only language tutor skill with broad routing language but no hidden code, persistence, credential access, or external actions.

Installers should expect this skill to steer many language, translation, grammar, and travel-phrase requests into a tutoring workflow. That broadness may be inconvenient in ambiguous conversations, but the inspected artifact does not show code execution, credential handling, data exfiltration, destructive behavior, or hidden persistence.

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
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill description is written with very broad activation language such as 'learn ANY language' and a long list of common learning intents, which can cause the router to invoke this skill for a wide range of generic requests. That increases the chance of misrouting and unintended skill activation, especially when user requests are ambiguous or overlap with translation, tutoring, travel, or writing-assistance domains.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The quick-command section contains many short, generic phrases like 'Explain [grammar concept]' and 'How do you say [phrase]?' that resemble ordinary user requests without any routing constraints. This broadens the match surface and can cause the skill to capture prompts outside its intended scope, leading to over-triggering and possible interference with safer or more appropriate skills.

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.