Discord

Security checks across malware telemetry and agentic risk

Overview

This Discord skill is purpose-aligned, but it exposes broad raw Discord API write/delete capability without enough documented guardrails.

Install only if you trust Membrane and are comfortable letting an agent act through your Discord permissions. Prefer prebuilt/read-only actions, grant the least-privileged Discord role or account possible, and require explicit approval before any POST, PUT, PATCH, or DELETE request.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The skill explicitly documents raw proxy requests to the Discord API, including support for POST, PUT, PATCH, and DELETE, without any warning about destructive operations, permission boundaries, or the need for user confirmation before modifying data. In an agent context, this increases the risk of unintended message deletion, channel changes, membership changes, or other state-altering actions being performed too readily.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal