ClawHub
Back to skill

Security audit

Torii Image Translator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow Torii Image Translator connector skill with disclosed account use and no bundled executable code, though users should be mindful that it can spend credits and send image data through OOMOL/Torii.

Install only if you intend to use OOMOL’s oo CLI with a connected Torii Image Translator account. Expect image URLs or payloads to be sent to Torii/OOMOL services, and confirm any action that consumes credits or creates modified images before running it.

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 Torii Image Translator request and whenever a task involves Torii Image Translator, which creates an overly broad trigger condition. This can cause the agent to invoke the skill even for casual mentions or contexts where direct use is unnecessary, increasing the chance of unintended external calls, privacy leakage, or user-intent mismatch.

Static analysis

No suspicious patterns detected.