ClawHub
Back to skill

Security audit

Unthread

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Unthread connector wrapper that can read and change Unthread account data, with explicit confirmation requirements for writes and deletion.

Install this only if you want your agent to manage Unthread account records through OOMOL. Review payloads carefully before approving create, update, or delete actions, especially delete_account because it is documented as permanent.

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
94% confidence
Finding
The description says to use this skill for ANY Unthread request and instead of calling the API directly, which creates an overly broad trigger surface. This can cause the agent to invoke the skill in situations where a narrower or safer handling path would be more appropriate, increasing the chance of unintended reads or state-changing operations if downstream user intent is ambiguous.

Static analysis

No suspicious patterns detected.