ClawHub
Back to skill

Security audit

Handelsregister AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Handelsregister AI connector wrapper with read-only listed actions and no hidden persistence or unrelated behavior.

Install only if you intend your agent to query Handelsregister AI through an OOMOL-connected account. Be aware that first-time setup may install or authenticate the oo CLI, and paid enrichment or billing errors may depend on your Handelsregister AI/OOMOL account configuration.

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 (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger text is overly broad: "Use this skill for ANY Handelsregister AI request" and "Whenever a task involves Handelsregister AI, use this skill instead of calling the API directly." This can cause the agent to route loosely related requests through the skill automatically, reducing user-intent validation and increasing the chance of unnecessary external data access or connector invocation in contexts where the skill is not actually required.

Static analysis

No suspicious patterns detected.