Security audit

iMessage

Security checks for vulnerabilities and agentic risk

Overview

This is a sensitive but coherent iMessage channel plugin that clearly centers on local Messages access and user-controlled sending.

Install only if you want OpenClaw to access your Messages database and send or manage iMessage/SMS conversations from a signed-in Mac. Review allowFrom, groupAllowFrom, dmPolicy, groupPolicy, actions, remoteHost, attachment roots, and native approval routing before enabling it, especially if exec approvals can be delivered through iMessage.

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/sanitize-outbound-C6UF2cvr.js:506
Evidence: const child = spawn(this.cliPath, args, { stdio: [

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: dist/monitor-Dj3TAimI.js:3069
Evidence: const storeAllowFrom = await readChannelAllowFromStore("imessage", process.env, accountInfo.accountId).catch(() => []);