@ouro.bot/cli@0.1.0-alpha.926
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 supports a warning for explicit user-command agent configuration: setup registers Ouro and writes hooks into Claude Code user settings. The manifest has no preinstall, install, or postinstall hook, and the inspected credential flow does not substantiate the scanner's redirect claim.
Decision evidence
public snapshot- The CLI parses setup as an explicit command; the manifest exposes CLI entrypoints and its scripts show no preinstall, install, or postinstall hook.
- Claude Code setup registers Ouro at user scope and writes hooks to the Claude settings file.
- The setup installs hooks for session start, session stop, and Bash, Edit, or Write actions.
- Other flagged integration locations concern local Codex auth-file reads, provider-aligned authentication, project MCP configuration, and plugin installation from a supplied source.
- The Claude configuration change is reached through the explicit setup command, not an npm install hook.
- The inspected credential flow uses the selected provider's endpoint; GitHub Copilot token discovery sends its token to api.github.com.
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.926.
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.926 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.