karajan-code@4.59.1
Local multi-agent coding orchestrator with TDD, SonarQube, and code review pipeline
AI Security Review
scanned 9h ago · by lpm-firewall-aiThe install hook silently configures a first-party MCP extension in global agent settings, leaving a meaningful agent-extension lifecycle risk. The inspected behavior supports a warning, but does not establish a concrete attack warranting a block.
Decision evidence
public snapshot- The manifest runs scripts/postinstall.js during npm installation.
- The hook registers the package’s MCP server in both Claude Code and Codex configuration without a consent prompt.
- The hook writes a karajan-mcp entry to the Claude Code user configuration and a matching block to the Codex user configuration.
- The registered server accepts agent tool calls and dispatches them to the package’s tools.
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@4.59.1.
See all versions of karajan-code for other recorded verdicts.
- Review the evidence and your use of karajan-code@4.59.1 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.