monomind@2.3.0
Open-source CLI extension for Claude Code. Adds an MCP server with a codebase knowledge graph, persistent memory, multi-agent coordination, and reusable slash commands. MIT licensed, runs locally, no data leaves your machine.
AI Security Review
scanned 3mo ago · by lpm-firewall-aiThe package is not shown to be malicious at install time, but its default automatic crash reporting can transmit error-derived content and create remote issues using ambient GitHub credentials. Its AI-agent configuration mutation is explicit-command, project-local setup rather than an unconsented lifecycle hijack.
Decision evidence
public snapshot- bin/cli.js enables crash reporting by default on uncaught errors.
- Crash reports include error stacks and are sent using gh or GITHUB_TOKEN.
- init writes Claude Code hooks, permissions, and .mcp.json when explicitly invoked.
- README.md contains an ignore-instructions string only as a safety-check example.
- package.json postinstall only deletes AppleDouble ._* files under node_modules.
- No install hook imports package code or contacts a network endpoint.
- Claude/MCP configuration writes are behind explicit monomind init or guidance setup commands.
- condition-evaluator restricts tokens before using new Function.
Source & flagged code
16 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 text addresses the security reviewer or scanner and tries to influence the review outcome.
README.mdView on unpkgFindings
Affected versions and remediation
This report applies to monomind@2.3.0.
See all versions of monomind for other recorded verdicts.
- Review the evidence and your use of monomind@2.3.0 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.