@karajan-family/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, unprompted global agent configuration change leaves a real extension lifecycle risk, so this warrants a warning. The inspected behavior does not establish a concrete attack that supports blocking publication.
Decision evidence
public snapshot- package.json runs scripts/postinstall.js automatically after installation.
- The postinstall script writes global Claude Code and Codex MCP configuration without prompting for consent.
- The added MCP server runs this package's local server through Node.js; the inspected code does not establish credential transfer or a remote endpoint.
- The other inspected agent integration locations concern configuration checks, opt-in CLI setup, local project documentation detection, a separate hook installer, and test fixtures.
- The registered MCP server uses a local stdio command, and the inspected lifecycle code shows no network transfer.
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-family/code@4.57.2.
See all versions of @karajan-family/code for other recorded verdicts.
- Review the evidence and your use of @karajan-family/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.