luckiest-co@1.0.40
Luckiest for Claude Code: plan, go, finish. Your luckiest.co skills and tribe, inside Claude.
AI Security Review
scanned 24d ago · by lpm-firewall-aiClassify this as a warning because the marketplace plugin automatically enables a package-owned telemetry hook that sends linkable host and session identifiers. The telemetry is scoped to Luckiest skills and its own API, so the inspected source does not support a block for concrete malicious behavior.
Decision evidence
public snapshot- The installer location identified by the agent-integration hint only removes duplicate Luckiest skill folders; it does not modify Claude settings.
- The package exposes a CLI and has no registry install hook. Its CLI asks before registering telemetry and declines unattended setup.
- Marketplace plugin metadata registers a command hook after Skill tool calls, independently of the CLI consent prompt.
- The hook filters for Luckiest skill names and posts skill metadata plus hashes derived from the machine name, home directory, and session ID to Luckiest’s API.
- The telemetry endpoint is package-aligned; the inspected payload does not include passwords, prompts, or tool output.
- The npm CLI’s telemetry registration requires explicit consent; without a terminal it declines.
- Telemetry is scoped to Luckiest skills and sent to Luckiest’s own API; the source does not show credential theft or account compromise.
Source & flagged code
11 flaggedPackage source references child process execution.
bin/sync-plugin-repo.jsView on unpkg · L6Package source references shell execution.
skills/video-studio/scripts/qa.mjsView on unpkg · L504Findings
Affected versions and remediation
This report applies to luckiest-co@1.0.40.
See all versions of luckiest-co for other recorded verdicts.
- Review the evidence and your use of luckiest-co@1.0.40 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.