@eventmodelers/cli@1.0.64
Eventmodelers CLI — real-time Claude agent + skills for Claude Code, for any stack (Node, Supabase, Axon, Cratis, OpenCQRS, UmaDB, Kurrent, or modeling-only)
AI Security Review
scanned 17d ago · by lpm-firewall-aiThe source shows a saved Eventmodelers token being handed to Claude without recipient binding or a recipient-specific consent gate. Because this requires an explicit agent run and is part of the package's CLI workflow, the evidence supports a warning rather than a block.
Decision evidence
public snapshot- The bridge runner reads saved configuration and includes the board token in a prompt when a board is configured.
- That token-bearing prompt is passed to Claude; the runner accepts a configurable Anthropic endpoint and has no recipient-specific gate.
- The bridge command selects the Claude runner when no hook, Ollama runner, or static adapter is selected.
- The default build-kit runner also places the configured token in Claude input and its environment; local mode suppresses the prompt header.
- Agent-host configuration is explicitly invoked through init-agents and writes stubs or copies installed skill files to selected host directories.
- The credential handoff occurs when a user starts an agent runner; the manifest identifies a CLI entry point, with no package lifecycle hook shown.
- The bridge can select a static adapter, Ollama, or a hook instead of Claude.
Source & flagged code
9 flaggedPackage source references child process execution.
stacks/bridge/templates/bridge/ralph-claude.jsView on unpkg · L8Package source references shell execution.
stacks/bridge/templates/bridge/ralph-hook.jsView on unpkg · L68Findings
Affected versions and remediation
This report applies to @eventmodelers/cli@1.0.64.
See all versions of @eventmodelers/cli for other recorded verdicts.
- Review the evidence and your use of @eventmodelers/cli@1.0.64 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.