ClawHub
Back to skill

Security audit

Autom

Security checks across malware telemetry and agentic risk

Overview

This is a small Autom connector skill that uses the OOMOL oo CLI for disclosed read-only Autom lookup and usage actions.

Before installing, understand that the skill expects you to use an OOMOL account connected to Autom and may read Autom usage, quota, rate limit, account, and API key metadata through the oo CLI. Only run the documented installer or login steps when you intentionally want to set up OOMOL/Autom access.

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
89% confidence
Finding
The instruction to use this skill for 'ANY Autom request' is overly broad and can cause the agent to invoke the skill in situations where direct API use, a different tool, or additional user confirmation would be more appropriate. Even though the listed actions are read-only here, broad routing language increases the chance of unintended activation and normalizes bypassing more precise tool-selection logic.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.