@ouro.bot/cli@0.1.0-alpha.900
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 12d ago · by lpm-firewall-aiSource inspection found a guarded, explicit-command Claude Code integration that changes user-level agent configuration. The flagged auth location reads local Codex credentials for provider authentication; the inspected excerpt does not show them sent to an unrelated destination.
Decision evidence
public snapshot- The package declares CLI entrypoints and no install lifecycle hook.
- The Claude Code integration runs only through the setup command path.
- That setup registers the package’s MCP server and writes hooks into the user’s Claude settings.
- The flagged auth flow reads the local Codex auth file for provider credentials.
- The inspected agent configuration change is explicitly command-triggered; the source does not establish an install-time or covert control-surface mutation.
Source & flagged code
16 flagged · loading sourcePackage contains a possible secret pattern.
dist/heart/daemon/cli-exec.jsView on unpkg · L3770Findings
Affected versions and remediation
This report applies to @ouro.bot/cli@0.1.0-alpha.900.
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.900 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.