ClawHub
Back to skill

Security audit

Kintone

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Kintone connector skill for read-oriented account data access, with one overly broad routing phrase but no evidence of hidden or destructive behavior.

Use this only if you are comfortable connecting Kintone to OOMOL and allowing read access to Kintone user and organization metadata. Keep usage to the listed read actions, verify the oo CLI installer before first-time setup, and require explicit confirmation if future connector schemas expose write or destructive actions.

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
90% confidence
Finding
The manifest description says to use this skill for "ANY Kintone request" and "instead of calling the API directly," which is an overly broad routing trigger. This can cause the agent to invoke the skill for all Kintone-related tasks without sufficient task-level scoping or user-intent checks, increasing the chance of unnecessary data access or bypassing safer, more specific handling paths.

Static analysis

No suspicious patterns detected.