@ouro.bot/cli@0.1.0-alpha.933
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 6d ago · by lpm-firewall-aiThe setup command explicitly mutates Claude Code configuration and overwrites existing hook arrays for three events, creating a risk of lost user handlers. The inspected credential flows target their corresponding services, and the manifest shows no install hook; the remaining finding supports a warning, not a block.
Decision evidence
public snapshot- The `setup` command is explicitly parsed with a selected tool; the manifest exposes CLI entrypoints and lists no install hook.
- Claude setup writes `~/.claude/settings.json` and replaces the SessionStart, Stop, and PostToolUse hook arrays with Ouro callbacks.
- Other flagged integration paths concern local Claude configuration, local Codex credentials and context files, or plugin installation from a supplied source.
- The inspected credential flow reads local Codex credentials, collects credentials through the selected provider flow, and sends refresh or Copilot requests to their corresponding service endpoints.
- The hook change requires an explicit setup command; no automatic install-time agent configuration change was identified.
- The credential paths inspected use the GitHub Copilot and OpenAI authentication endpoints; no unrelated credential recipient was established.
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.933.
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.933 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.