karajan-code@4.55.0
Local multi-agent coding orchestrator with TDD, SonarQube, and code review pipeline
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe postinstall hook automatically changes user-level agent configuration to register this package's MCP server, leaving a lifecycle extension risk. The inspected behavior supports a warning, but does not establish a concrete attack.
Decision evidence
public snapshot- package.json runs scripts/postinstall.js as the npm postinstall hook.
- The postinstall routine sets up both Claude and Codex MCP configurations without a user prompt in that routine.
- The Claude configuration is written with a local command that starts this package's MCP server.
- The Codex configuration is updated with an MCP entry that starts this package's local server.
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@4.55.0.
See all versions of karajan-code for other recorded verdicts.
- Review the evidence and your use of karajan-code@4.55.0 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.