@raolin2025/claude-code-node@2.8.11
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 2mo ago · by lpm-firewall-aiThe package contains a real, user-invoked remote shell interface with missing Telegram access control. Its explicit remote-programming purpose and absence of lifecycle execution support a warning rather than a malware block.
Decision evidence
public snapshot- Telegram messages are forwarded to the daemon handler with no sender/chat allow-list check observed.
- The Telegram /run command executes supplied shell text directly.
- The daemon has a second /run path using execSync and returns command output to Telegram.
- The risky listener starts only when the user runs cc-notify and configures a Telegram token.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- No package-controlled exfiltration endpoint was found; Telegram use is configured by the user.
- Permission persistence is limited to this package's .claude-code directory.
Source & flagged code
11 flagged · loading sourceFindings
Affected versions and remediation
This report applies to @raolin2025/claude-code-node@2.8.11.
See all versions of @raolin2025/claude-code-node for other recorded verdicts.
- Review the evidence and your use of @raolin2025/claude-code-node@2.8.11 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.