karajan-code@4.45.0
Local multi-agent coding orchestrator with TDD, SonarQube, and code review pipeline
AI Security Review
scanned 14d ago · by lpm-firewall-aiThe automatic postinstall mutation of global agent configuration is a concrete lifecycle risk. The inspected behavior is first-party MCP setup, so it warrants a warning rather than a block.
Decision evidence
public snapshot- package.json runs scripts/postinstall.js during npm installation.
- The postinstall hook automatically writes a karajan-mcp server entry to the user's global Claude and Codex configurations.
- The Codex entry launches this package's own MCP server over stdio; the inspected server identifies itself as karajan-mcp.
- This is automatic first-party agent integration, a guarded lifecycle risk; the inspected code does not establish exfiltration or destructive behavior.
- The hook adds or replaces only the package-named karajan-mcp entry in each configuration.
- The configured server is launched locally with node and uses stdio transport.
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@4.45.0.
See all versions of karajan-code for other recorded verdicts.
- Review the evidence and your use of karajan-code@4.45.0 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.