@luckydraw/cumulus@1.0.32
RLM-based CLI chat wrapper for Claude with external history context management
AI Security Review
scanned 3d ago · by lpm-firewall-aiSource inspection found package-aligned gateway and agent functionality, interactive service setup, and ordinary build hooks. The scanner’s persistence and execution signals did not establish an unconsented attack.
Decision evidence
public snapshot- The manifest’s prepare hook runs Husky, and prepublishOnly runs build and type checking; no install-time payload or consumer policy mutation is shown.
- The flagged project setup reaches auto-start service installation through an interactive TTY prompt.
- Gateway and agent runtime operations are message handling, context processing, and configured MCP setup; the account-action callers deliver requested or scheduled agent turns.
- The flagged subprocess hook manages the Claude process for a user message.
- The version check queries the npm registry for package release information.
- The gateway widget is a packaged web-chat asset, and the Mermaid bundle identifies itself as a vendored library.
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@1.0.32.
See all versions of @luckydraw/cumulus for other recorded verdicts.
- Review the evidence and your use of @luckydraw/cumulus@1.0.32 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.