@raolin2025/claude-code-node@3.6.9
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 16d ago · by lpm-firewall-aiSource inspection did not substantiate the scanner’s exfiltration or install-time control-surface claims. The flagged credential operations are explicit product functions directed to their corresponding services, and the package has no npm lifecycle hook.
Decision evidence
public snapshot- The manifest defines CLI entrypoints but no install lifecycle hook.
- The suspicious notifier request is invoked by the configured Telegram channel and targets the Telegram API.
- The npm publishing tool reads a local npm token and sends it to registry.npmjs.org for publishing.
- The permission module persists permission rules locally; the SSRF guard blocks loopback and private ranges.
- The Bash tool exposes command execution as an explicitly invoked agent tool.
- The scheduler exposes task creation and execution through its scheduler interface.
- The notifier supports remote programming features, but inspected network and credential behavior is tied to its configured messaging service.
- No inspected source established an automatic credential transfer to an unrelated recipient or unconsented install-time control-surface mutation.
Source & flagged code
15 flagged · loading sourcePackage contains a critical-looking secret pattern.
src/__tests__/dream.test.jsView on unpkg · L421GitHub personal access token in src/__tests__/dream.test.js
src/__tests__/dream.test.jsView on unpkg · L421GitHub personal access token in src/__tests__/dream.test.js
src/__tests__/dream.test.jsView on unpkg · L437Findings
Affected versions and remediation
This report applies to @raolin2025/claude-code-node@3.6.9.
See all versions of @raolin2025/claude-code-node for other recorded verdicts.
- Review the evidence and your use of @raolin2025/claude-code-node@3.6.9 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.