ClawHub
Back to skill

Security audit

Discord Bot

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Discord Bot connector, but it needs review because some state-changing actions are left untagged while the skill says untagged actions are safe to run directly.

Install only if you want an agent to operate your Discord Bot through OOMOL. Review the bot's Discord permissions and OOMOL connection carefully, and require explicit confirmation for any action that posts, pins, crossposts, unbans, prunes members, changes roles or channels, or deletes data, even if the skill does not label that action as write or destructive.

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 skill description is overly broad: it instructs agents to use this skill for ANY Discord Bot request, without narrowing scope by task type, authorization context, or risk level. In an agentic system, this can cause over-selection of a high-privilege connector for loosely related Discord requests, increasing the chance of unintended reads, writes, or destructive operations being routed through the skill.

VirusTotal

52/52 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.