ClawHub
Back to skill

Security audit

Autom

Security checks across malware telemetry and agentic risk

Overview

This skill is a narrowly scoped Autom connector guide that uses the OOMOL CLI for read-only Autom lookups and usage checks, with credential handling disclosed.

Install this only if you want agents to query Autom through your OOMOL-connected account. Be aware that usage checks can reveal account, quota, rate-limit, and API-key metadata, and first-time setup may require trusting the OOMOL CLI installation and login flow.

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
93% confidence
Finding
The description says to use this skill for ANY Autom request, which is an overly broad routing trigger and can cause the agent to invoke the skill in situations where a narrower or safer tool choice would be more appropriate. Broad trigger phrases increase the attack surface for prompt-injection-style misuse and can lead to unnecessary execution of external commands or access to connected account data without sufficiently specific user intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.