@spuentesp/lain-mcp@0.9.0
High-performance knowledge graph MCP server for AI coding agents with semantic search.
AI Security Review
scanned 13d ago · by lpm-firewall-aiThe install-time binary download and execution match the package’s stated purpose, and the inspected installer verifies the archive checksum before extraction. No concrete attack behavior was found in the inspected source.
Decision evidence
public snapshot- The package’s postinstall invokes its installer, which skips downloading in CI unless forced and when npm scripts are disabled.
- The installer downloads versioned releases from the project’s GitHub repository and verifies the archive against its listed SHA-256 checksum.
- The launcher runs the downloaded Lain binary with the caller’s arguments and working directory, consistent with the package’s stated MCP server purpose.
Source & flagged code
5 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time source downloads a native archive from a fixed external host without transport verification, extracts it, and installs an executable payload.
package.jsonView on unpkg · L2Findings
Affected versions and remediation
This report applies to @spuentesp/lain-mcp@0.9.0.
See all versions of @spuentesp/lain-mcp for other recorded verdicts.
- Review the evidence and your use of @spuentesp/lain-mcp@0.9.0 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.