ClawHub
Back to skill

Security audit

Raygun

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Raygun connector skill with scoped OOMOL CLI use and confirmation requirements for changes or deletes.

Install this only if you intend to let OOMOL’s Raygun connector act on your connected Raygun account. Review the Raygun scopes on the OOMOL connection, and require explicit approval before creating, updating, or deleting deployments.

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 activation text says to use this skill for ANY Raygun request and instead of calling the API directly, which is broad enough to capture all Raygun-related tasks without narrowing scope by operation type or user intent. In agent environments, overly broad routing increases the chance of unintended invocation for sensitive read, write, or destructive actions, especially when combined with a connector that has authenticated access.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.