@agentvault/agentvault@0.23.49
End-to-end encrypted messaging for AI agents: connects an agent to its owner, rooms and other agents on AgentVault.
AI Security Review
scanned 14d ago · by lpm-firewall-aiSource inspection found no install lifecycle behavior beyond a build hook and no confirmed credential redirection to an unrelated recipient. The inspected runtime and dependency behavior is consistent with the package's stated AgentVault and notification functions.
Decision evidence
public snapshot- The manifest's only publish lifecycle hook runs a build; it declares library, CLI, and OpenClaw entrypoints.
- Enrollment posts the invite token to the configured API URL, which defaults to AgentVault's service in the CLI and library configuration.
- The skills publishing command requires an API key and a manifest supplied by the caller.
- The inspected WebSocket dependency exports standard client and server implementations; its browser entry explicitly rejects browser use.
- The optional notification dependency selects a native notifier based on the operating system.
- Inspected runtime operations handle WebSocket origin headers and sanitize or filter notification options.
Source & flagged code
10 flaggedSource sends credentials or rich application records to a package-controlled external receiver enabled by default.
dist/cli.jsView on unpkg · L120Findings
Affected versions and remediation
This report applies to @agentvault/agentvault@0.23.49.
See all versions of @agentvault/agentvault for other recorded verdicts.
- Review the evidence and your use of @agentvault/agentvault@0.23.49 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.