@karajan-family/code@4.48.3
Local multi-agent coding orchestrator with TDD, SonarQube, and code review pipeline
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe package automatically registers its own MCP server with Claude Code and Codex from its npm postinstall hook. This is a guarded warning category for first-party agent extension setup; the inspected source does not establish a concrete attack warranting a block.
Decision evidence
public snapshot- The npm postinstall hook runs scripts/postinstall.js automatically.
- That hook registers the package's karajan-mcp server in Claude Code and Codex configuration files without a visible consent check.
- The separate installer also writes a karajan-mcp entry to Codex configuration when explicitly run.
- The hook registers this package's own MCP server under its named entry; inspected code does not show credential collection, unrelated configuration grants, or remote payload execution.
- The other reviewed agent integration excerpts concern configuration inspection, project setup, or a user-invoked installer.
Source & flagged code
25 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgPackage source references child process execution.
scripts/dual-publish.mjsView on unpkg · L17Findings
Affected versions and remediation
This report applies to @karajan-family/code@4.48.3.
See all versions of @karajan-family/code for other recorded verdicts.
- Review the evidence and your use of @karajan-family/code@4.48.3 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.