Security audit

Discord

Security checks across malware telemetry and agentic risk

Overview

This official OpenClaw Discord plugin is coherent with its purpose and exposes expected Discord bot capabilities with configuration gates, though users should scope it carefully.

Install only for Discord servers and channels you intend OpenClaw to access. Keep the bot token secret, use guild/channel allowlists and actions gates, disable moderation/presence/thread-spawn/voice features you do not need, and confirm destructive actions such as delete, edit, pin, role, channel, kick, or ban operations before asking an agent to run them.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill explicitly documents destructive actions such as delete, edit, pin, and thread creation without any caution about authorization, confirmation, auditability, or irreversible effects. In an agent setting, this increases the chance that an LLM or operator will perform harmful state-changing actions in the wrong channel or on the wrong message, especially because the examples make these actions look routine and low-friction.

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The skill describes read and search capabilities over Discord content without warning that these operations may expose private messages, sensitive internal discussions, or data from channels the user did not intend to query. In a multi-account, multi-guild environment, omission of privacy constraints makes accidental overcollection and inappropriate disclosure more likely.

VirusTotal

62/62 vendors flagged this plugin as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: dist/manager.runtime-DaB-CTrt.js:97
Evidence: const ffmpeg = spawn(resolveFfmpegBin(), [

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: dist/provider-BkfbC9FQ.js:6092
Evidence: env: process.env