@ouro.bot/cli@0.1.0-alpha.928
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 8d ago · by lpm-firewall-aiSource inspection found a user-invoked setup path that changes global Claude Code settings and forwards limited session content to a local agent. This supports a warning for agent configuration capability, but the inspected behavior does not establish an automatic install-time attack or unrelated credential disclosure.
Decision evidence
public snapshot- The CLI parser requires a tool argument and returns a setup command, making this an explicit user-invoked setup path.
- Claude Code setup targets the user's .claude directory and writes lifecycle hooks into settings.json.
- Those hooks send session metadata and up to 200 characters of the last assistant message to the selected agent through the local daemon socket.
- Plugin installation uses a supplied source; enabling a plugin for an agent occurs only when an agent is specified.
- The changelog describes loading MCP server declarations from installed plugins.
- The inspected Codex credential code reads local auth data and uses OpenAI's authentication endpoint for refresh.
- The hook requires the explicit setup command and sends its message through a local daemon socket; this inspection found no external collector in that path.
- The credential-related excerpts show local Codex auth data and an OpenAI authentication endpoint, not a redirect to an unrelated recipient.
Source & flagged code
16 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.928.
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.928 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.