Security audit

Discord

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Discord integration that uses expected Discord bot credentials and permissions, with disclosed controls for message, moderation, voice, and channel features.

Install only for Discord servers and bot permissions you intend OpenClaw to control. Keep the bot token secret, restrict guild/channel/user allowlists, leave moderation, channel administration, privileged intents, voice, auto-join, and activity secrets disabled unless needed, and review action gates before letting agents perform destructive actions.

SkillSpector

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

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: dist/voice-runtime-DMYDMkJx.js:129
Evidence: const ffmpeg = spawn(resolveFfmpegBin(), [

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: dist/provider-DmRHCZ_K.js:6297
Evidence: const gatewayInfoTimeoutMs = resolveDiscordGatewayInfoTimeoutMs({ env: process.env });