@oked/claude-code@0.6.2
OKed for Claude Code - zero-code human approval for sensitive actions
AI Security Review
scanned 28d ago · by lpm-firewall-aiSource inspection shows project configuration and device pairing are activated by the explicit init command; package.json has no install-time hook. The scanner's process and network signals are consistent with this CLI behavior, and no concrete attack was established.
Decision evidence
public snapshot- The package exposes CLI commands and has no install lifecycle hook; its listed scripts are build and prepublishOnly tasks.
- The indicated settings path is the current project's .claude/settings.json, and init adds or updates the OKed hook there.
- Pairing sends a device code request to the configured OKed backend, defaulting to api.oked.ai.
- Hook installation runs through the explicit init command.
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@0.6.2.
See all versions of @oked/claude-code for other recorded verdicts.
- Review the evidence and your use of @oked/claude-code@0.6.2 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.