@clawos-dev/clawd@0.2.629
Standalone clawd daemon — Claude Code (and future Codex) session server over WebSocket
AI Security Review
scanned 14d ago · by lpm-firewall-aiThe package manifest has no install lifecycle hook, and the inspected flagged source locations show package functionality rather than an attack chain. Scanner similarity and generic dynamic-code signals did not establish malicious behavior in the source reviewed.
Decision evidence
public snapshot- package.json defines a CLI entry point and no preinstall, install, or postinstall hook.
- The app-builder location constructs a Claude skill script path for a publish helper; it does not show an installer or agent configuration write.
- The CLI location appends a turn-duration row to the current Claude project session JSONL file.
- The remaining flagged files contain bundled runtime code or dispatch logic; inspected source showed no concrete attack behavior.
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@0.2.629.
See all versions of @clawos-dev/clawd for other recorded verdicts.
- Review the evidence and your use of @clawos-dev/clawd@0.2.629 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.