Security audit

Discord

Security checks for vulnerabilities and agentic risk

Overview

This is a purpose-aligned Discord connector that needs a bot token and can act in configured servers, with sensitive capabilities disclosed and configurable.

Install only for Discord servers and channels you intend OpenClaw to operate in. Use a least-privileged bot token, stable user IDs in allowlists, narrow guild/channel/voice scopes, and leave advanced features such as moderation, role/channel management, presence tracking, auto-join voice, realtime voice, and thread-bound session spawning disabled unless you need them.

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/.setup/receive-recovery-DgkX7Qvi.mjs:119
Evidence: const ffmpeg = spawn(resolveFfmpegBin(), [

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: dist/.setup/provider-YP8gN9_o.mjs:6052
Evidence: const gatewayInfoTimeoutMs = resolveDiscordGatewayInfoTimeoutMs({ env: process.env });