ClawHub
Back to skill

Security audit

Breezy HR

Security checks across malware telemetry and agentic risk

Overview

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

Install this only if you intend to let the OOMOL oo connector read Breezy HR records available to your connected account. Be careful with candidate and user-profile data, inspect action schemas before use, and do not run first-time setup or billing/auth steps unless you are comfortable connecting Breezy HR through OOMOL.

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 description says to use this skill for ANY Breezy HR request and instead of calling the API directly, which creates an overly broad routing trigger. That can cause the agent to invoke this skill for loosely related requests and route sensitive HR data access through a shell-based connector path without enough task-specific validation, increasing the chance of inappropriate data retrieval or unnecessary exposure.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.