@raolin2025/claude-code-node@3.6.20
Node.js AI Code Agent CLI - Zero dependencies, pure JavaScript, security hardened, multi-channel notifications, Telegram & QQ Bot remote programming, rich media upload, multi-account management
AI Security Review
scanned 3d ago · by lpm-firewall-aiSource inspection found no install-time attack behavior or confirmed malicious runtime activity. The token-related code serves explicit npm status and publishing actions, with requests directed to the npm registry.
Decision evidence
public snapshot- The manifest exposes CLI entrypoints and has only a prepublishOnly check, with no install hook.
- The npm publishing helper reads the local npm token and uses it for requests to the npm registry; publishing is an explicit action on an ask-permission tool.
- The status and publish callers use the token for npm status or publishing, and the manual-publish action invokes the direct publish helper.
- The flagged i18n and multiline-input operations interpolate strings and calculate terminal cursor positions.
- Inspected runtime paths implement command safety checks, scheduling, local notification key setup, SSRF protections, permission checks, MCP command allowlisting, QQ/Telegram integrations, and process helpers.
Source & flagged code
20 flagged · loading sourceSource file is highly similar to a previously finalized malicious package; route for source-aware review.
src/tools/bash.jsView on unpkgFindings
Affected versions and remediation
This report applies to @raolin2025/claude-code-node@3.6.20.
See all versions of @raolin2025/claude-code-node for other recorded verdicts.
- Review the evidence and your use of @raolin2025/claude-code-node@3.6.20 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.