karajan-code@4.53.1
Local multi-agent coding orchestrator with TDD, SonarQube, and code review pipeline
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe package automatically modifies global agent configuration during npm installation to register its own MCP server. This is a first-party agent extension setup with residual lifecycle risk, so warn without blocking; the inspected source does not establish a concrete attack.
Decision evidence
public snapshot- The package manifest runs scripts/postinstall.js during installation.
- The postinstall handler registers the package's MCP server in both Claude Code and Codex configuration files.
- The Codex registration is written to the user's home configuration without an interactive consent check in the postinstall path.
- The registered server is the package's own MCP server; the inspected source does not establish credential theft, data exfiltration, or other malicious behavior.
Source & flagged code
24 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-code@4.53.1.
See all versions of karajan-code for other recorded verdicts.
- Review the evidence and your use of karajan-code@4.53.1 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.