ClawHub
Back to skill

Security audit

Brex

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Brex read-only connector skill that uses OOMOL's oo CLI, with no evidence of hidden persistence, exfiltration, or destructive behavior.

Install only if you are comfortable connecting Brex through OOMOL and letting the agent read sensitive Brex financial and employee-related data via the oo CLI. Review OOMOL CLI installation and Brex connection scopes before use, and ask for explicit confirmation before any future state-changing Brex action even though this version lists only read actions.

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 trigger text says to use this skill for ANY Brex request and instead of calling the API directly, which creates an overly broad routing rule with weak scope boundaries. In practice this can cause unrelated or higher-risk Brex tasks to be funneled through a generic shell-backed connector workflow without sufficient task-level constraints, increasing the chance of unintended data access or misuse.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.