@raolin2025/claude-code-node@3.6.13
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 12d ago · by lpm-firewall-aiThe inspected manifest has no automatic install hook, and the flagged source behavior is consistent with an invoked CLI agent, authenticated notification interface, and explicit npm publishing tool. No source evidence established covert credential exfiltration or another concrete attack.
Decision evidence
public snapshot- package.json declares a prepublishOnly check, not an install hook.
- The Bash tool runs a safety check before executing a caller-supplied command.
- The scheduler exposes task operations through an explicit scheduler interface.
- The notification server rejects API requests with an invalid key.
- The publish tool reads an npm token and sends it to the npm registry for publishing.
- The SSRF guard checks addresses, and the permission module stores permission rules locally.
- The notification daemon can route authenticated HTTP or messaging input into the agent.
- The publish tool handles a local npm credential and provides publishing operations.
Source & flagged code
12 flagged · loading sourceThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
src/tools/bash.jsView on unpkgFindings
Affected versions and remediation
This report applies to @raolin2025/claude-code-node@3.6.13.
See all versions of @raolin2025/claude-code-node for other recorded verdicts.
- Review the evidence and your use of @raolin2025/claude-code-node@3.6.13 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.