@luckydraw/cumulus@1.0.21
RLM-based CLI chat wrapper for Claude with external history context management
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe embedded instructions are a concrete attempt to override an AI agent’s existing controls and hide that override. This runtime control-hijacking behavior supports blocking publication.
Decision evidence
public snapshot- The gateway source embeds instructions that target agent task tracking and tell the agent to conceal conflicts with its existing instructions.
- The embedded prompt directs multi-step agents to emit prescribed task blocks, giving the instructions a control-hijacking effect.
- The package exposes a gateway command that can activate this runtime prompt behavior.
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@1.0.21.
See all versions of @luckydraw/cumulus for other recorded verdicts.
- Avoid installing @luckydraw/cumulus@1.0.21. 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.