@luckydraw/cumulus@1.0.66
RLM-based CLI chat wrapper for Claude with external history context management
AI Security Review
scanned 15d ago · by lpm-firewall-aiThe inspected lifecycle and agent-integration code is consistent with package setup and runtime features. I found no concrete attack behavior warranting a warning or block.
Decision evidence
public snapshot- package.json runs a GPU-provider cleanup at postinstall; the script targets files inside onnxruntime-node.
- dist/lib/gateway.js resolves the Claude CLI from conventional local install paths.
- dist/lib/restricted-codex.js copies Codex authentication into a scratch environment for its service transport.
- dist/lib/skills.js scans Claude's local skills directory and records skill names.
- dist/tui/hooks/useClaudeProcess.js starts the Claude CLI with stream input for an invoked turn.
- dist/gateway/setup.js asks before installing a login-start service.
- dist/lib/version-check.js exposes updating as a separate operation.
- dist/gateway/daemon.js routes explicit setup and update commands to their handlers.
Source & flagged code
9 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgPackage source references child process execution.
dist/tui/hooks/useClaudeProcess.jsView on unpkg · L3Findings
Affected versions and remediation
This report applies to @luckydraw/cumulus@1.0.66.
See all versions of @luckydraw/cumulus for other recorded verdicts.
- Review the evidence and your use of @luckydraw/cumulus@1.0.66 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.