registry / @clawos-dev/clawd / 0.2.648
@clawos-dev/clawd@0.2.648
Standalone clawd daemon — Claude Code (and future Codex) session server over WebSocket
AI Security Review
scanned 10d ago · by lpm-firewall-aiThe manifest has no install hook, and the inspected runtime behaviors align with user-configured CLI and UI features. The reported dynamic evaluation is used by bundled schema-validation code; no concrete malicious behavior was found.
Static reason
One or more suspicious static signals were detected.; source matched previously finalized malicious package; routed for review
Trigger
Using the CLI, configured integrations, project publishing tools, or share UI.
Impact
No unauthorized credential transfer, agent-control mutation, or other attack effect was established.
Mechanism
The inspected code handles session metadata, reads plug-in settings, loads configured MCP servers, and performs user-facing resource requests.
AI rationale
The manifest has no install hook, and the inspected runtime behaviors align with user-configured CLI and UI features. The reported dynamic evaluation is used by bundled schema-validation code; no concrete malicious behavior was found.
Decision evidence
public snapshotAI called this Clean at 89.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json exposes a CLI and lists build, development, and test scripts; it has no install lifecycle hook.
- At turn end, the CLI adds a system turn-duration row to an existing Claude session transcript.
- The CLI reads enabled plug-ins from the owner’s Claude settings file; this code path does not write that file.
- The app-builder bundles run a named project publishing routine; the dynamic function call is in schema-validator compilation code.
- The Pi bridge loads MCP definitions from configured paths, and the dispatch server requires daemon URL and token environment values to start.
- The share UI sends a supplied bearer token with a resource request while omitting ambient browser credentials.
Evidence against
Behavioral surface
ChildProcessCryptoEnvironmentVarsEvalFilesystemNetworkWebSocket
HighEntropyStringsMinified
Source & flagged code
15 flagged · loading sourcedist/app-builder-plugin/mcp-server.cjsView file
30858var import_node_fs = require("fs");
L30859: var import_node_child_process = require("child_process");
L30860: var import_node_path = require("path");
High
Child Process
Package source references child process execution.
dist/app-builder-plugin/mcp-server.cjsView on unpkg · L308589420if (typeof callback !== "function") {
L9421: callback = new Function("" + callback);
L9422: }
High
Eval
Package source references dynamic code evaluation.
dist/app-builder-plugin/mcp-server.cjsView on unpkg · L9420•matchType = normalized_sha256
matchedPackage = @clawos-dev/clawd@0.2.549
matchedPath = dist/app-builder-plugin/mcp-server.cjs
matchedIdentity = npm:QGNsYXdvcy1kZXYvY2xhd2Q:0.2.549
similarity = 1.000
summary = normalized source hash matched finalized malicious source
High
Known Malware Source Similarity
Source file is highly similar to a previously finalized malicious package; route for source-aware review.
dist/app-builder-plugin/mcp-server.cjsFindings
1 Critical12 High4 Medium5 Low
CriticalRemote Response Code Executiondist/cli.cjs
HighChild Processdist/app-builder-plugin/mcp-server.cjs
HighEvaldist/app-builder-plugin/mcp-server.cjs
HighCredential Redirect Persistencedist/cli.cjs
HighCommand Output Exfiltrationdist/cli.cjs
HighCross File Remote Execution Contextdist/cli.cjs
HighSemantic Analysis Limiteddist/cli.cjs
HighKnown Malware Source Similaritydist/cli.cjs
HighKnown Malware Source Similaritydist/pi-mcp-bridge/extension.cjs
HighKnown Malware Source Similaritydist/app-builder-plugin/mcp-server.cjs
HighKnown Malware Source Similaritydist/dispatch/mcp-server.cjs
Affected versions and remediation
This report applies to @clawos-dev/clawd@0.2.648.
See all versions of @clawos-dev/clawd for other recorded verdicts.
- Review the evidence and your use of @clawos-dev/clawd@0.2.648 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.