ClawHub
Back to skill

Security audit

SimpleLocalize

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed SimpleLocalize connector helper with read, write, and delete actions that are scoped to the user's connected account and require confirmation for changes.

Install this only if you want Codex to manage your connected SimpleLocalize project through OOMOL. Review write and delete payloads carefully before approving them, especially language deletion or translation updates.

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
86% confidence
Finding
The skill description says to use this skill for ANY SimpleLocalize request, which creates an overly broad trigger scope and can cause the agent to invoke it whenever SimpleLocalize is mentioned, even when the user did not intend connector-backed actions. In a skill that supports read, write, and destructive operations, this broad routing increases the chance of unnecessary tool use and accidental state-changing workflows being selected without sufficient scope narrowing.

Static analysis

No suspicious patterns detected.