@karajan-family/code@4.51.0
Local multi-agent coding orchestrator with TDD, SonarQube, and code review pipeline
AI Security Review
scanned 10d ago · by lpm-firewall-aiThe postinstall hook silently mutates two AI-agent configuration files to enable this package’s own MCP server. This is a guarded-category lifecycle risk for warning, but the inspected behavior does not establish a broader control-surface attack warranting a block.
Decision evidence
public snapshot- package.json runs scripts/postinstall.js after installation.
- The hook automatically registers the package’s MCP server in Claude Code and Codex configuration.
- The registrations point to this package’s local MCP server and use named configuration entries.
- The related ai-trash hook installer requires an explicit kj-trash install --claude-code command.
- The inspected postinstall hook shows configuration writes, but no network transfer or credential collection.
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@4.51.0.
See all versions of @karajan-family/code for other recorded verdicts.
- Review the evidence and your use of @karajan-family/code@4.51.0 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.