ClawHub

Discord Markdown

Security checks across malware telemetry and agentic risk

Overview

This is a Discord formatting helper that only provides Markdown instructions and templates; it does not run code, access accounts, or post messages automatically.

Safe to install as a formatting/reference helper. Before pasting generated text into Discord, review @everyone, @here, role mentions, masked links, and message length to avoid accidental broad notifications or unintended public content.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description is broad enough that it may activate for many generic Discord-related requests, not just formatting tasks. Over-broad invocation can cause the agent to apply this skill in inappropriate contexts, potentially reshaping outputs or introducing Discord-specific constructs such as mentions, links, or markdown when the user did not intend that behavior.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill teaches and exemplifies Discord mentions, including high-reach patterns like @everyone and role mentions, but does not warn about the disruptive impact of mass pings. In a message-generation context, that omission increases the chance the agent will produce content that triggers unwanted notifications across a server, creating social engineering, spam, or operational disruption risks.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal