@karajan-family/code@4.43.0
Local multi-agent coding orchestrator with TDD, SonarQube, and code review pipeline
AI Security Review
scanned 5d ago · by lpm-firewall-aiSource inspection confirms that installation automatically changes global agent configuration to register the package's own MCP server. This is a first-party extension setup with residual consent risk, so it warrants a warning; the inspected source does not establish a concrete malicious attack.
Decision evidence
public snapshot- The package manifest runs scripts/postinstall.js automatically after installation.
- That hook registers the package's local stdio MCP server in the global Claude and Codex configurations without asking first.
- The registered server exposes tools for running the package's coding pipeline.
- Other inspected agent integration locations cover configuration checks, project-scoped MCP wiring, or separate setup paths.
- The configured MCP server is a local stdio process; the inspected registration code does not send credentials to a remote endpoint.
- The separate installer and trash hook setup are exposed through distinct setup paths, not the postinstall registration.
Source & flagged code
25 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-family/code@4.43.0.
See all versions of @karajan-family/code for other recorded verdicts.
- Review the evidence and your use of @karajan-family/code@4.43.0 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.