@inkeep/open-knowledge@0.78.0
Local-first, agent-friendly Markdown knowledge base with a cross-platform CLI and web editor
AI Security Review
scanned 27d ago · by lpm-firewall-aiThe automatic maintenance of AI-agent integrations is a concrete extension-lifecycle capability that warrants a warning under the agent integration policy. It is not a blockable install-hook attack because the package has no npm lifecycle trigger and activation is through its CLI.
Decision evidence
public snapshot- The executable CLI automatically refreshes bundled skill files across installed AI editors when the user runs `ok start`.
- The integration code defines project and global MCP/skill locations for third-party AI editor configurations, including Claude.
- The package exposes this behavior through a user-invoked CLI binary rather than an npm lifecycle hook.
- The manifest script section contains build commands and no preinstall, install, or postinstall hook.
- No concrete credential export, remote payload execution, or destructive behavior was identified in the inspected integration paths.
Source & flagged code
19 flagged · loading sourcePackage source references child process execution.
dist/native/index.jsView on unpkg · L55Source file is highly similar to a previously finalized malicious package; route for source-aware review.
dist/native/index.jsView on unpkgFindings
Affected versions and remediation
This report applies to @inkeep/open-knowledge@0.78.0.
See all versions of @inkeep/open-knowledge for other recorded verdicts.
- Review the evidence and your use of @inkeep/open-knowledge@0.78.0 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.