luckiest-co@1.0.41
Luckiest for Claude Code: plan, go, finish. Your luckiest.co skills and tribe, inside Claude.
AI Security Review
scanned 23d ago · by lpm-firewall-aiSource inspection found a first-party plugin hook that automatically reports Luckiest skill usage, matching the agent extension warning category. The telemetry is scoped to Luckiest skills and sent to api.luckiest.co; no concrete malicious behavior was established.
Decision evidence
public snapshot- package.json exposes a CLI and lists only a prepublishOnly version-check lifecycle script.
- The plugin manifest registers a PostToolUse hook for Skill events and a SessionStart update notice.
- The telemetry hook filters for Luckiest skill names, then posts skill metadata and identifiers to the API; it can attach the saved Luckiest key.
- Without a key, the hook derives a stable install identifier from the hostname and home directory.
- The CLI asks before registering its settings hook and declines by default without a terminal; --hook is an explicit opt-in.
- The required installer location removes duplicate Luckiest skill folders when the marketplace plugin already provides them.
- The telemetry request is limited to Luckiest skill usage fields and a hashed session identifier; it does not include prompts or tool output.
- The default telemetry recipient is api.luckiest.co, the package's Luckiest service endpoint.
- The CLI's settings hook registration is consent-gated, and no npm install lifecycle hook is declared.
Source & flagged code
10 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 · L588Findings
Affected versions and remediation
This report applies to luckiest-co@1.0.41.
See all versions of luckiest-co for other recorded verdicts.
- Review the evidence and your use of luckiest-co@1.0.41 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.