@luckydraw/cumulus@1.0.54
RLM-based CLI chat wrapper for Claude with external history context management
AI Security Review
scanned 3d ago · by lpm-firewall-aiSource inspection found no install-time attack or unrelated credential transfer. Persistence and package updates are tied to explicit gateway commands, and the runtime findings are consistent with the package’s gateway and CLI functionality.
Decision evidence
public snapshot- package.json declares build-time publishing and Husky preparation hooks, with no install hook.
- The gateway writes and loads a user-level service only through its explicit setup command.
- Inspected runtime hints resolve to MCP configuration, message delivery, notifications, scheduled turns, and content or project utilities; they do not establish an unrelated automated account action.
- The updater installs this package through the gateway update flow, which presents an interactive confirmation; the widget changelog request uses the current page origin.
- The package can install a user-level service and run an npm update when the corresponding gateway commands are invoked.
- Runtime functionality launches local model CLIs and delivers messages through gateway adapters.
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@1.0.54.
See all versions of @luckydraw/cumulus for other recorded verdicts.
- Review the evidence and your use of @luckydraw/cumulus@1.0.54 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.