ClawHub
Back to skill

Security audit

Opsgenie

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be an Opsgenie-focused integration with no malware telemetry or artifact-backed evidence of hidden, destructive, or unrelated behavior.

Install only if you intend to let the agent work with Opsgenie. Keep credentials scoped to the minimum Opsgenie permissions needed, and require explicit confirmation before creating, acknowledging, closing, or otherwise changing alerts.

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 description explicitly says to use this skill for ANY Opsgenie request and whenever a task involves Opsgenie, which is an overly broad routing trigger. That can cause the agent to invoke this skill even for vague mentions or mixed-intent tasks, increasing the chance of unintended external actions or unnecessary exposure of operational data. In this context, the skill supports both read and write actions against an incident-management system, so mistaken invocation is more consequential than for a read-only reference skill.

VirusTotal

57/57 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.