Security audit

PLUR1BUS Memory: Make your agent yours

Security checks for vulnerabilities and agentic risk

Overview

This is a broad but disclosed OpenClaw memory plugin that stores and recalls conversations and sets up background jobs; I found no evidence of hidden exfiltration or destructive intent.

Install only if you want this agent to keep long-term conversation memory and run background maintenance jobs. Review defaults for autoCapture, autoRecall, featureCronSetup.auto, skillMiner.autoApply, and security.allowModelDestructiveMemoryOps, and configure allowedUserIds/allowedChatIds before using shared chat channels.

SkillSpector

SkillSpector was not run because this plugin release contains no bundled skills.

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: index.js:3599
Evidence: child = spawn(process.execPath, [scriptPath, "--json"], {

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/lib/openclaw-cli.mjs:17
Evidence: const r = spawnSync("openclaw", args, { encoding: "utf8", timeout, ...(options.env ? { env: options.env } : {}) });

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: index.js:697
Evidence: const v = process.env[envVar];