ClawHub
Back to skill

Security audit

AnyDB

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AnyDB connector that uses OOMOL's oo CLI for read and confirmed write actions, with no hidden persistence or unrelated behavior found.

Install this only if you intend your agent to operate AnyDB through OOMOL. Review write payloads carefully before approving create or update actions, and only use the first-time CLI install and account connection steps if you trust OOMOL's oo CLI and want it connected to your AnyDB account.

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 language is explicitly universal: 'Use this skill for ANY AnyDB request' and 'Whenever a task involves AnyDB, use this skill instead of calling the API directly.' That can cause the agent to invoke this skill for a very broad class of requests without sufficient routing discrimination, increasing the chance of unintended access to connected data or accidental execution of write-capable actions in contexts where a narrower skill or additional checks would be more appropriate.

Static analysis

No suspicious patterns detected.