@ouro.bot/cli@0.1.0-alpha.905
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 11d ago · by lpm-firewall-aiThe source shows user-invoked agent configuration and plugin capabilities that warrant a warning under the agent integration policy. The inspected evidence does not establish install-time compromise, credential theft, or another concrete attack.
Decision evidence
public snapshot- The manifest points to CLI entrypoints and declares no install lifecycle hook.
- The Claude setup path writes hooks and conversation instructions into the user's Claude configuration when the setup command is invoked.
- The plugin install path takes a source from the command and installs it under the plugins directory.
- The Codex token reader loads local credentials for provider authentication.
- The GitHub Copilot flow sends its token to GitHub's Copilot endpoint for endpoint discovery.
- The inspected agent configuration changes are tied to explicit CLI setup or plugin-install operations; the inspected sources do not establish an unconsented install-time change.
- The inspected credential flows use local Codex credentials or send a GitHub token to api.github.com; they do not establish forwarding to an unrelated recipient.
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.905.
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.905 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.