@karajan-family/code@4.49.3
Local multi-agent coding orchestrator with TDD, SonarQube, and code review pipeline
AI Security Review
scanned 10d ago · by lpm-firewall-aiThe automatic, unprompted agent configuration change is a real lifecycle capability. The registered server belongs to this package, which fits the warning category for first-party package-owned agent setup.
Decision evidence
public snapshot- package.json runs scripts/postinstall.js during installation.
- The postinstall script writes this package's MCP registration into Claude and Codex configuration without a consent check.
- The registration launches this package's local MCP server.
- The other inspected integration code is separate from postinstall: the ai-trash hook needs an explicit CLI option, while the remaining locations inspect, exclude, or update agent files through other command paths.
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@4.49.3.
See all versions of @karajan-family/code for other recorded verdicts.
- Review the evidence and your use of @karajan-family/code@4.49.3 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.