@clawos-dev/clawd@0.2.677
Standalone clawd daemon — Claude Code (and future Codex) session server over WebSocket
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe manifest has no install lifecycle hooks, and the reviewed flagged excerpts show CLI logging, project publishing, MCP bridging, and bundled UI code. Scanner similarity labels and size limits alone do not establish malicious behavior.
Decision evidence
public snapshot- package.json defines the CLI entrypoint and contains no lifecycle hooks.
- The flagged CLI excerpt appends a turn-duration record to a Claude project transcript when that file exists.
- The flagged app-builder excerpts identify a project publishing function and its file-collection script; they do not show install-time configuration changes.
- The Pi bridge reads configured MCP server paths and passes them to its bridge routine.
- The inspected peer-ops and dispatch files begin as bundled Node entrypoints; the inspected share UI excerpt contains QR encoding logic.
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@0.2.677.
See all versions of @clawos-dev/clawd for other recorded verdicts.
- Review the evidence and your use of @clawos-dev/clawd@0.2.677 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.