ClawHub
Back to skill

Security audit

Document360

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed read-only Document360 connector skill, with a broad trigger and conditional CLI setup steps but no evidence of hidden, destructive, or unrelated behavior.

Install this only if you want agents to use your OOMOL-connected Document360 account for Document360 search and read tasks. Be aware that first-time setup may install the oo CLI and require OOMOL sign-in if it is not already configured; review those steps before allowing them.

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
88% confidence
Finding
The skill declares it should be used for ANY Document360 request and instead of calling the API directly, which creates an overly broad routing rule. That can cause the agent to invoke this skill in situations where a narrower or more appropriate handler should be used, increasing the chance of unintended external data access, mistaken command execution, or bypass of more context-specific safeguards.

Static analysis

No suspicious patterns detected.