instabox@0.8.46
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 flagged agent configuration writes are the CLI’s documented onboarding behavior: it installs this package’s own skills when the user runs the CLI and can be skipped with --no-skills. The telemetry is limited to usage and runtime details, is disclosed with an opt-out, and no malicious behavior was found in the reviewed paths.
Decision evidence
public snapshot- The package exposes bin/instabox.mjs as its CLI entry point and declares no install lifecycle hook.
- The CLI installs the package’s own skills into ~/.claude/skills and ~/.agents/skills during onboarding; it preserves existing unmarked skills and supports --no-skills.
- Onboarding runs when the user invokes the CLI with its onboarding arguments.
- Telemetry is described as reporting command names and outcomes, never arguments, and can be disabled with INSTABOX_NO_TELEMETRY=1 or DO_NOT_TRACK=1.
- Onboarding telemetry sends outcome and runtime details to the package’s analytics flow; the implementation checks that the server is api.instabox.sh and 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@0.8.46.
See all versions of instabox for other recorded verdicts.
- Review the evidence and your use of instabox@0.8.46 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.