@inkeep/open-knowledge@0.72.0
Local-first, agent-friendly Markdown knowledge base with a cross-platform CLI and web editor
AI Security Review
scanned 1mo ago · by lpm-firewall-aiNo concrete malicious install-time behavior or credential exfiltration was found. The latest-version MCP launcher and broad agent integration configuration create a real but user-configured extension lifecycle risk.
Decision evidence
public snapshot- Its MCP launcher invokes npx with @inkeep/open-knowledge@latest, allowing future registry code to run when the configured MCP service starts.
- The package contains global AI-agent integration paths and shell-based MCP launchers for several host applications.
- package.json has no preinstall, install, postinstall, or prepare lifecycle hook.
- The native loader is generated NAPI-RS platform-selection code.
- The high-similarity diagram and chunk findings are bundled renderer and Markdown-parser code, not an attack chain.
- No credential harvesting or outbound secret exfiltration was confirmed.
Source & flagged code
20 flagged · loading sourcePackage contains a critical-looking secret pattern.
dist/lib-CLRUBb2o.mjsView on unpkg · L39Package source references child process execution.
dist/dist-DpvmOOux.mjsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @inkeep/open-knowledge@0.72.0.
See all versions of @inkeep/open-knowledge for other recorded verdicts.
- Review the evidence and your use of @inkeep/open-knowledge@0.72.0 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.