@luckydraw/cumulus@1.0.26
⚠ Under reviewRLM-based CLI chat wrapper for Claude with external history context management
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe manifest and inspected excerpts show expected setup, update, and gateway behavior, with no confirmed attack. Required runtime and account-action paths remain untraced, so the evidence is insufficient to mark the package clean or to assign a warning or block.
Decision evidence
public snapshot- The manifest defines build, prepublishOnly, and prepare scripts, but no preinstall, install, or postinstall hook.
- Gateway setup is presented as an explicit setup command; the update function installs a specified version of this package when invoked.
- The inspected runtime code generates MCP configuration and starts local Claude execution; automated agent turns are queued when a thread is busy.
- The full runtime review remains unresolved: relevant account-action callers and required runtime locations were not all traced, so the inspected excerpts do not establish a clean verdict.
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@1.0.26.
See all versions of @luckydraw/cumulus for other recorded verdicts.
- Review the evidence and your use of @luckydraw/cumulus@1.0.26 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.