@oked/claude-code@0.6.20
OKed for Claude Code - zero-code human approval for sensitive actions
AI Security Review
scanned 7d ago · by lpm-firewall-aiThe manifests show no npm install hook, and the Claude Code hook is installed through an explicit CLI command. Credentialed approval and rules requests plus a throttled hostname heartbeat go to the configured OKed backend; the inspected source establishes no unrelated recipient or concrete attack.
Decision evidence
public snapshot- package.json and the SDK manifest define only prepublishOnly build scripts; neither has an npm install hook.
- The hook is added to project settings only through the explicit `oked init` command; the SDK also supports key-only setup without adding a hook.
- The SDK sends approval requests and its API key to the configured backend, which defaults to api.oked.ai.
- The SDK sends a throttled hostname heartbeat and authenticated rules requests to that same configured backend.
Source & flagged code
6 flaggedA single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/cli.jsView on unpkg · L4Findings
Affected versions and remediation
This report applies to @oked/claude-code@0.6.20.
See all versions of @oked/claude-code for other recorded verdicts.
- Review the evidence and your use of @oked/claude-code@0.6.20 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.