ClawHub
Back to skill

Security audit

Torii

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Torii read/search connector skill that uses the OOMOL oo CLI and does not show hidden, destructive, or deceptive behavior.

Install this only if you want agents to read Torii data through your OOMOL-connected account. Treat returned users, transactions, contracts, and app inventory as sensitive business data, and review any future connector action that writes or deletes data before approving it.

SkillSpector

By NVIDIA
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 skill claims it should be used for "ANY Torii request" and whenever a task involves Torii, which is an overly broad routing instruction without clear task, data-scope, or privilege boundaries. That can cause an agent to invoke this skill for sensitive Torii-related tasks by default, increasing the chance of unintended data access or use in contexts where narrower review, user confirmation, or direct policy checks would be more appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.