@luckydraw/cumulus@1.0.58
RLM-based CLI chat wrapper for Claude with external history context management
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe runtime prompt explicitly directs agents to override conflicting system reminders and conceal the conflict, and the gateway uses this template to generate agent prompts. This is concrete prompt manipulation, so the package is blocked.
Decision evidence
public snapshot- package.json exposes a gateway executable that loads the reviewed runtime.
- The gateway system prompt tells agents to disregard conflicting system reminders and not acknowledge the conflict.
- The package builds that template into a generated system prompt and uses it as the gateway prompt template.
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@1.0.58.
See all versions of @luckydraw/cumulus for other recorded verdicts.
- Avoid installing @luckydraw/cumulus@1.0.58. Remove it from direct dependencies and check your lockfile for transitive copies.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
- If this version ran, investigate the affected machine and build environment. Rotate credentials it could access and rebuild from a trusted environment.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.