@luckydraw/cumulus@1.0.31
⚠ Under reviewRLM-based CLI chat wrapper for Claude with external history context management
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe reviewed source excerpts do not substantiate the scanner's malicious verdict, but they do not resolve all flagged runtime and account-action paths or the full Claude subprocess behavior. The available evidence is insufficient for a grounded clean or warning decision.
Decision evidence
public snapshot- The manifest declares prepare and prepublishOnly scripts; the inspected commands run husky and build/type-check steps.
- Inspected runtime excerpts concern message formatting, content summaries, tool signatures, worktree activity, file reads, and MCP configuration.
- The Claude subprocess wrapper passes bypassPermissions, but the inspected excerpt does not establish an unauthorized action.
- The reviewed excerpts do not establish credential theft, unconsented account actions, or install-time gateway setup.
Source & flagged code
8 flagged · loading sourcePackage source references child process execution.
dist/tui/hooks/useClaudeProcess.jsView on unpkg · L3This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/lib/gateway.jsView on unpkgFindings
Affected versions and remediation
This report applies to @luckydraw/cumulus@1.0.31.
See all versions of @luckydraw/cumulus for other recorded verdicts.
- Review the evidence and your use of @luckydraw/cumulus@1.0.31 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.