karajan-code@4.53.0
Local multi-agent coding orchestrator with TDD, SonarQube, and code review pipeline
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe automatic postinstall mutation creates a persistent agent integration without an interactive consent check, leaving residual lifecycle risk. The inspected server is this package’s own MCP server, and the source reviewed does not establish a concrete attack.
Decision evidence
public snapshot- The package postinstall hook automatically runs scripts/postinstall.js.
- The hook writes a karajan-mcp server entry to the global Codex configuration and invokes setup for both Codex and Claude.
- The registered server exposes tools and handles agent tool calls, creating a persistent agent integration without an interactive consent check.
- The hook registers this package’s own MCP server; the inspected source does not establish credential theft or another active attack.
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@4.53.0.
See all versions of karajan-code for other recorded verdicts.
- Review the evidence and your use of karajan-code@4.53.0 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.