@luckydraw/cumulus@1.0.2
RLM-based CLI chat wrapper for Claude with external history context management
AI Security Review
scanned 3mo ago · by lpm-firewall-aiThe package is an agentic CLI/gateway, so the risky primitives are product-aligned and user-triggered rather than evidence of malware. Its unguarded capability design warrants a warning, not a publication block.
Decision evidence
public snapshot- dist/lib/gateway.js launches Claude with bypassPermissions.
- dist/lib/tools/bash.js executes model-requested bash commands.
- dist/lib/tools/write.js permits absolute-path file writes.
- dist/lib/mcp-client-tools.js launches configured MCP commands with inherited environment.
- package.json has no preinstall/install/postinstall hook.
- Gateway persistence is only behind explicit cumulus-gateway setup prompts.
- Runtime update uses a fixed package name and explicit update command.
- No hard-coded exfiltration endpoint or covert payload loading found.
Source & flagged code
8 flagged · loading sourcePackage source references child process execution.
dist/tui/hooks/useClaudeProcess.jsView on unpkg · L3Findings
Affected versions and remediation
This report applies to @luckydraw/cumulus@1.0.2.
See all versions of @luckydraw/cumulus for other recorded verdicts.
- Review the evidence and your use of @luckydraw/cumulus@1.0.2 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.