ClawHub
Back to skill

Security audit

Dutch

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Dutch-writing style guide with no code, tools, persistence, credential use, or hidden data access.

Install this if you want help producing natural, casual Dutch. Be aware it may make Dutch text more informal by default, so explicitly ask for formal Dutch, customer-service tone, or u-vorm when needed.

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 instructs the agent to produce Dutch in a specific casual style by default, without requiring explicit user opt-in or checking the user's requested language. This can cause unauthorized behavior override, where the model ignores user language preference or silently transforms outputs into Dutch, reducing reliability and potentially causing miscommunication in multilingual or safety-critical contexts.

Vague Triggers

Low
Confidence
86% confidence
Finding
This markdown file describes the skill's purpose ('Dutch') and behavior but does not specify when it should be invoked, what requests it applies to, or any negative examples. For a markdown skill description, the absence of explicit trigger boundaries can make invocation conditions ambiguous and overly broad.

Static analysis

No suspicious patterns detected.