ClawHub
Back to skill

Security audit

CATS

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed, read-only CATS connector wrapper that uses the OOMOL CLI and does not include hidden persistence, destructive behavior, or malware telemetry hits.

Install only if you intend to let the agent read data from your connected CATS account through OOMOL. Review the external oo CLI setup step and remember that candidate and hiring data may be sensitive even when the skill is read-only.

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
88% confidence
Finding
The skill description instructs the agent to use this skill for ANY CATS-related request, creating an overly broad routing rule with no scope guardrails. That can cause the agent to invoke the skill in situations where direct API use, additional validation, or a different workflow would be safer, increasing the chance of inappropriate data access or unintended operations if the skill later expands beyond read-only behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.