karajan-code@4.57.2
Local multi-agent coding orchestrator with TDD, SonarQube, and code review pipeline
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe automatic user-wide MCP registration leaves a real agent-extension lifecycle risk, so a warning is appropriate. The inspected source does not support a malicious verdict or publication block.
Decision evidence
public snapshot- package.json runs scripts/postinstall.js automatically after installation.
- The postinstall path calls both Claude and Codex setup functions without a consent check and writes their user-wide MCP configuration files.
- The registered service is a local stdio MCP server that lists tools and handles tool calls; no external endpoint is established by this registration path.
- Other inspected agent-related code covers explicit CLI setup, an init prompt, fixture setup, inventory or validation, and project-document reading; it does not remove the postinstall 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@4.57.2.
See all versions of karajan-code for other recorded verdicts.
- Review the evidence and your use of karajan-code@4.57.2 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.