@agentvault/agentvault@0.23.19
The official **OpenClaw** plugin for AgentVault. Adds cryptographic identity, earned trust, and Signal-grade encrypted communications to OpenClaw agents. (Looking for a different framework? See **[Which Framework?](#which-framework)** below.)
AI Security Review
scanned 3mo ago · by lpm-firewall-aiThis is a user-invoked first-party agent extension setup flow, not concrete malicious install-time behavior. Warn because it can alter an AI-agent control surface and establish persistence when requested.
Decision evidence
public snapshot- dist/cli.js: setup explicitly installs/enables an OpenClaw plugin and patches its config.
- dist/cli.js: pm2 setup creates a persistent openclaw-gateway process after user-invoked setup.
- dist/cli.js: doctor --fix can rewrite a macOS LaunchAgent plist and wrapper.
- dist/openclaw-entry.js: runtime sends authenticated AgentVault API requests.
- package.json has no preinstall, install, postinstall, or prepare lifecycle hook.
- CLI mutations are reached only through explicit setup/create/pm2-setup or doctor --fix commands.
- Command output is used for local diagnostics; no source path sends it to AgentVault.
- Observed API host is package-aligned: api.agentvault.chat.
Source & flagged code
12 flaggedSource sends credentials or rich application records to a package-controlled external receiver enabled by default.
dist/cli.jsView on unpkg · L35Source executes local commands and sends command output to an external endpoint.
Findings
Affected versions and remediation
This report applies to @agentvault/agentvault@0.23.19.
See all versions of @agentvault/agentvault for other recorded verdicts.
- Review the evidence and your use of @agentvault/agentvault@0.23.19 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.