@luckydraw/cumulus@1.0.49
RLM-based CLI chat wrapper for Claude with external history context management
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe scanner flags map to expected build hooks, prompted gateway service setup, and an explicitly invoked self-update operation. Reviewed runtime message and configuration paths did not establish credential theft, unauthorized account changes, or another concrete attack.
Decision evidence
public snapshot- package.json limits its lifecycle hooks to building and type checking before publish and setting up Husky; neither performs consumer-project mutation on registry install.
- Gateway service persistence is reached from the explicit setup command and offered only through an interactive prompt; the service runs the gateway at login.
- The npm install command is inside the exported update operation and installs this package at the version passed to that operation.
- Inspected runtime paths build MCP configuration and send messages through the configured thread pipeline; the account-action hints are message delivery or configuration plumbing, not independent account changes.
- The remaining inspected runtime targets cover project context, thread operations, tool configuration, job output, and UI assets; no concrete attack behavior was identified.
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@1.0.49.
See all versions of @luckydraw/cumulus for other recorded verdicts.
- Review the evidence and your use of @luckydraw/cumulus@1.0.49 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.