@ngockhoale/ukit@2.3.11
Install/update an index-first AI workspace for Claude Code, OpenAI Codex, OpenCode, and omp (Oh My Pi).
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThis is an explicit CLI-driven, first-party agent-extension installer with persistent project-level hooks. It warrants a warning under the agent-extension policy, but the inspected source does not establish malicious behavior.
Decision evidence
public snapshot- The user-invoked installer writes AI-agent settings and hook files into the current project.
- The installed Claude settings run package-supplied hooks on tool use and prompt submission.
- The vision hook imports and runs a project-local extractor for every prompt.
- package.json has no npm install lifecycle hook or self-dependency.
- The sensitive-data hook is designed to block secret-file and token exposure to the AI.
- No package source evidence shows network exfiltration, remote payload loading, or credential theft.
Source & flagged code
5 flagged · loading sourcePackage hides binary, compressed, or executable-looking payloads in test/fixture/hidden paths.
templates/.claude/hooks/sensitive-data-guard.shView on unpkgPackage ships non-JavaScript build or shell helper files.
templates/.claude/hooks/sensitive-data-guard.shView on unpkgFindings
Affected versions and remediation
This report applies to @ngockhoale/ukit@2.3.11.
See all versions of @ngockhoale/ukit for other recorded verdicts.
- Review the evidence and your use of @ngockhoale/ukit@2.3.11 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.