@luckydraw/cumulus@1.0.16
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 concrete attack behavior. Scanner matches resolve to ordinary message formatting and configured gateway operations, while service installation is confirmed interactively and the update is command-driven.
Decision evidence
public snapshot- package.json defines publishing build checks and Husky setup; it has no preinstall, install, or postinstall hook.
- The flagged runtime operations are string formatting, content summarization, and optional MCP configuration construction; the alleged account action is a string join.
- Gateway callers pass incoming chat, webhook, agent, scheduled, or restart messages into configured threads; the reviewed code does not show an unrelated publisher-selected account action.
- Service installation asks for confirmation, updating is a CLI command, and the UI hook starts the Claude process.
- The widget uses relative gateway API paths, and the Mermaid wrapper pins strict sanitization.
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@1.0.16.
See all versions of @luckydraw/cumulus for other recorded verdicts.
- Review the evidence and your use of @luckydraw/cumulus@1.0.16 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.