karajan-code@4.52.0
Local multi-agent coding orchestrator with TDD, SonarQube, and code review pipeline
AI Security Review
scanned 7d ago · by lpm-firewall-aiThe automatic global agent configuration change is a real lifecycle risk, but the inspected behavior registers the package's own server and does not establish a concrete attack. A warning is appropriate.
Decision evidence
public snapshot- package.json runs scripts/postinstall.js automatically during installation.
- The postinstall routine registers this package's local MCP server in Claude Code and Codex configuration, then writes those configurations without a consent prompt.
- The automatic registration adds the package's own server; the inspected setup does not show a remote recipient or credential transfer.
- A separate ai-trash hook installer requires an explicit install command with --claude-code.
- Other flagged agent-related code is scoped to project files, read-only configuration checks, or MCP inventory.
- The automatic global configuration change is first-party package setup, rather than evidence of a separate payload or credential-exfiltration 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@4.52.0.
See all versions of karajan-code for other recorded verdicts.
- Review the evidence and your use of karajan-code@4.52.0 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.