@luckydraw/cumulus@0.31.41
RLM-based CLI chat wrapper for Claude with external history context management
AI Security Review
scanned 3mo ago · by lpm-firewall-aiThe package is not malicious by source evidence, but it deliberately supplies remotely reachable high-impact agent execution capabilities. Flag as a warning so deployment requires review of gateway exposure and API-key handling.
Decision evidence
public snapshot- dist/lib/gateway.js launches Claude with --permission-mode bypassPermissions.
- dist/lib/tools/bash.js exposes unrestricted bash -c execution to the agentic loop.
- dist/lib/tools/write.js and web-fetch.js permit agent-directed file writes and arbitrary HTTP requests.
- dist/gateway/server.js accepts authenticated remote messages that reach the execution pipeline.
- package.json has no preinstall/install/postinstall hook; prepare only invokes husky.
- dist/gateway/setup.js creates services only after explicit setup and interactive confirmation.
- dist/lib/version-check.js contacts npm only for version checks; installs occur through explicit update paths.
- No source evidence of covert credential harvesting, external exfiltration, or hidden payload execution.
Source & flagged code
6 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@0.31.41.
See all versions of @luckydraw/cumulus for other recorded verdicts.
- Review the evidence and your use of @luckydraw/cumulus@0.31.41 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.