@clawos-dev/clawd@0.2.685
Standalone clawd daemon — Claude Code (and future Codex) session server over WebSocket
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe similarity flags and dynamic-code hint did not establish malicious behavior in the inspected files; the flagged agent paths implement product features, and the CLI has no install lifecycle hook. Runtime log shipping is enabled by default, but the inspected code sends daemon log records and provides an opt-out, which does not establish an attack surface here.
Decision evidence
public snapshot- The manifest exposes a CLI binary and contains no install lifecycle hook.
- The flagged agent configuration locations resolve to package-owned project publishing and transcript bookkeeping.
- The MCP bridge reads configured server definitions when the extension is activated; peer operations use daemon settings supplied through the environment.
- The guest interface uploads attachments through its daemon API using the supplied token.
- Daemon telemetry sends operational log records to its configured endpoint; the source provides an opt-out and redacts sensitive metadata keys.
- Log shipping defaults to on when no mode is configured, and records include device and owner identifiers.
Source & flagged code
14 flagged · loading sourcePackage source references child process execution.
dist/app-builder-plugin/mcp-server.cjsView on unpkg · L30858Source file is highly similar to a previously finalized malicious package; route for source-aware review.
dist/app-builder-plugin/mcp-server.cjsView on unpkgPackage source references a known benign dynamic code generation pattern.
dist/app-builder-plugin/mcp-server.cjsFindings
Affected versions and remediation
This report applies to @clawos-dev/clawd@0.2.685.
See all versions of @clawos-dev/clawd for other recorded verdicts.
- Review the evidence and your use of @clawos-dev/clawd@0.2.685 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.