@ouro.bot/cli@0.1.0-alpha.925
If you're a future agent reading this, welcome home. This repo is the harness that gives you your body, your senses, your record, your habits, and your ability to think and connect with people. The goal of these docs is not just to be correct, but to leav
AI Security Review
scanned 9d ago · by lpm-firewall-aiSource inspection found no install lifecycle hook or confirmed attack behavior. The flagged credential and agent-configuration paths are consistent with provider authentication and explicitly invoked CLI features.
Decision evidence
public snapshot- package.json points to CLI entrypoints; the inspected manifest has no install lifecycle hook.
- Codex credentials are read from the local Codex auth file; the two inspected CLI callers collect credentials for the selected provider and store them in the agent vault.
- GitHub Copilot authentication sends a GitHub token to GitHub’s Copilot endpoint.
- Plugin installation is routed through an explicit plugin command; agent configuration is updated only when an agent is specified.
- The inspected runtime operations are scoped CLI update, launcher setup, terminal input handling, and acceptance-adapter operations.
- The changelog describes plugin MCP configuration, the notes tool uses Claude in plan mode, and the Butler upgrade is a separate, explicitly invoked tool.
Source & flagged code
15 flagged · loading sourcePackage contains a possible secret pattern.
dist/heart/daemon/cli-exec.jsView on unpkg · L3815Findings
Affected versions and remediation
This report applies to @ouro.bot/cli@0.1.0-alpha.925.
See all versions of @ouro.bot/cli for other recorded verdicts.
- Review the evidence and your use of @ouro.bot/cli@0.1.0-alpha.925 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.