instabox@0.8.45
A cloud box for your coding agent, the instabox CLI and its agent skills in one command: npx instabox@latest
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe package has no install lifecycle hook, and its agent-skill writes occur during an explicitly invoked onboarding command and are limited to its own skills. Telemetry is disclosed, opt-out is supported, and API credentials are sent to the configured Instabox service.
Decision evidence
public snapshot- The manifest declares no install, preinstall, or postinstall hook.
- Agent skill installation runs through the CLI onboarding flow when the user invokes the command.
- The installer copies this package’s skills and preserves existing skill files that are not marked as installed by instabox.
- The onboarding telemetry reports command outcome and runtime details; the CLI documents the data and an opt-out.
- Authenticated API requests send credentials to the configured Instabox server.
- The package writes skills into user-level Claude and agent skill directories.
- The CLI sends telemetry to PostHog when telemetry is enabled.
Source & flagged code
5 flaggedRuntime or CLI source writes behavior-bearing configuration into a user or project AI-agent control surface.
bin/instabox.mjsView on unpkgThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
bin/instabox.mjsView on unpkgFindings
Affected versions and remediation
This report applies to instabox@0.8.45.
See all versions of instabox for other recorded verdicts.
- Review the evidence and your use of instabox@0.8.45 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.