@clawos-dev/clawd@0.2.631
Standalone clawd daemon — Claude Code (and future Codex) session server over WebSocket
AI Security Review
scanned 14d ago · by lpm-firewall-aiStatic inspection found no install lifecycle hook or concrete malicious behavior. The flagged Claude paths correspond to project publishing and session logging, while the reviewed wrapper files showed no attack behavior.
Decision evidence
public snapshot- package.json defines a CLI entrypoint and no install lifecycle hook; its scripts are build and development tasks.
- The .claude path in the app-builder server points to a package skill script invoked during project publishing.
- The CLI writes a turn-duration row to the current Claude project session log.
- The pi bridge and dispatch server files begin with ordinary CommonJS wrapper code.
- The CLI reads the owner’s Claude settings file, but the inspected code only parses it; no malicious use was established.
- Static hints about similarity, evaluation, and network calls were not substantiated as attack behavior in the inspected source.
Source & flagged code
15 flagged · loading sourcePackage source references child process execution.
dist/app-builder-plugin/mcp-server.cjsView on unpkg · L21117Source file is highly similar to a previously finalized malicious package; route for source-aware review.
dist/app-builder-plugin/mcp-server.cjsView on unpkgFindings
Affected versions and remediation
This report applies to @clawos-dev/clawd@0.2.631.
See all versions of @clawos-dev/clawd for other recorded verdicts.
- Review the evidence and your use of @clawos-dev/clawd@0.2.631 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.