@clawos-dev/clawd@0.2.555
Standalone clawd daemon — Claude Code (and future Codex) session server over WebSocket
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe code establishes a real remote-code-execution capability on a user-triggered path. It is not enough to prove malware intent or justify an install-time block, but it is unsafe enough to warn.
Decision evidence
public snapshot- The CLI downloads a shell script from a package-controlled portal without an integrity or signature check.
- It passes the downloaded response directly to Bash, with the caller-provided pool API key placed in that process environment.
- The engine RPC handler accepts an API key and invokes that remote-script path.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The risky path is an engine connection action, not automatic installation-time execution.
Source & flagged code
19 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 unpkgPackage contains a possible secret pattern.
dist/app-builder-plugin/mcp-server.cjsView on unpkg · L24903Findings
Affected versions and remediation
This report applies to @clawos-dev/clawd@0.2.555.
See all versions of @clawos-dev/clawd for other recorded verdicts.
- Review the evidence and your use of @clawos-dev/clawd@0.2.555 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.