ClawHub
Back to skill

Security audit

Slovenian

Security checks for vulnerabilities and agentic risk

Overview

This is a benign Slovenian writing-style skill whose main caveat is that it intentionally nudges output toward casual language unless formality is requested.

Install this if you want Slovenian output to sound casual and native-like. For business, legal, academic, or respectful contexts, explicitly ask for formal Slovenian, Vi, or a professional register.

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)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill sets a default Slovenian style and register without requiring user choice, effectively enforcing informal output whenever triggered. This can produce responses that are inappropriate for professional, formal, or user-specified contexts, making the skill a source of unintended behavior rather than a neutral writing aid.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The description is broad enough to match many generic requests involving Slovenian writing, which can cause the skill to activate outside a clearly scoped use case. That increases the chance of unintended style steering, overriding user intent, or interfering with unrelated tasks that merely mention Slovenian.

Static analysis

No suspicious patterns detected.