Security audit

Discord Chat

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only Discord skill with broad but visible messaging and channel-management powers, so users should limit bot permissions and confirm destructive actions.

Install only for a Discord bot and server you control. Grant the bot the minimum permissions needed, keep tokens in environment variables or a secret manager, and require explicit user confirmation before sending public messages, editing or deleting messages, pinning content, or creating, moving, or deleting channels.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (8)

Description-Behavior Mismatch

Medium

Confidence: 94% confidence
Finding: The manifest description advertises only send/reply/search behavior, while the body also documents read, react, edit, delete, and channel enumeration actions. This capability mismatch can cause the skill to be invoked under a narrower expectation than what it can actually do, increasing the risk of unintended destructive or privacy-sensitive operations.

Description-Behavior Mismatch

High

Confidence: 97% confidence
Finding: The file documents powerful Discord administrative actions such as channel creation, editing, moving, deleting, category management, thread management, and permission inspection, which materially exceed the skill's declared scope of sending/replying/searching messages. This creates a scope-expansion hazard: an agent or operator relying on the docs may invoke destructive or privilege-sensitive actions the user did not intend, including permanent channel deletion and structural server changes.

Intent-Code Divergence

Medium

Confidence: 94% confidence
Finding: The title and introduction present the skill as 'Discord Channel Management,' directly conflicting with the stated skill purpose of chat messaging and search. This mismatch increases the likelihood that downstream users or agents will treat administrative channel operations as in-scope, causing unauthorized or unsafe actions through confusion rather than explicit approval.

Description-Behavior Mismatch

Medium

Confidence: 93% confidence
Finding: The documentation expands the skill’s effective operating scope beyond the stated Discord chat purpose by describing channel enumeration, metadata lookup, inbound webhook handling, and gateway-level configuration mutation. In an agent-skill context, this can normalize or encourage use of capabilities that increase privilege, broaden data access, or alter infrastructure outside the expected send/reply/search boundary.

Context-Inappropriate Capability

Medium

Confidence: 95% confidence
Finding: Including gateway configuration patching and live credential replacement in a chat skill reference exposes privileged operational procedures that are not necessary for normal Discord messaging. If surfaced to an agent or user in the wrong context, this could facilitate unauthorized credential changes, service disruption, or misuse of secrets-handling pathways.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The description uses broad trigger language such as handling general Discord communication, activity checks, and interaction with channels, which can over-match many routine user requests. Over-broad invocation increases the chance the agent selects this skill in contexts where write, read, or moderation-like actions were not intended, expanding exposure to accidental data access or message modification.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill documents a delete action with no warning, confirmation requirement, or guidance that deletion is destructive and potentially irreversible. In an agent setting, this makes accidental or prompt-induced message deletion more likely, which can cause loss of records, moderation issues, or operational disruption in shared Discord channels.

Missing User Warnings

Low

Confidence: 84% confidence
Finding: The example shows replacing a live Discord bot token via a config patch without emphasizing that this changes production credentials and must be handled as a secret. Even as documentation, this can lead to unsafe practices such as pasting tokens into command histories, logs, or tickets, increasing the chance of credential exposure or accidental service interruption.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.