@ouro.bot/cli@0.1.0-alpha.829
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 5d ago · by lpm-firewall-aiThe concrete residual risk is the explicit setup command's persistent mutation of Claude Code hooks, including replacement of existing hooks for affected events. The reviewed auth and plugin paths did not establish an independent attack.
Decision evidence
public snapshot- The setup path is an explicit CLI command that requires a selected tool and agent.
- Claude Code setup writes persistent session and tool hooks into its settings file, replacing existing hook lists for those events.
- The auth command gathers credentials through provider-specific prompts or local login, then stores them in the agent credential store; the inspected GitHub token request goes to GitHub.
- Plugin installation is dispatched as a separate CLI command and uses the source supplied to that command.
- The flagged Telegram operation redacts private values from error text.
- The manifest exposes CLI entrypoints and contains no install lifecycle hook.
- The inspected auth flow did not show credentials being sent to an unrelated recipient.
- The setup and plugin changes require explicit CLI commands; the inspected sources did not establish automatic setup during package installation.
Source & flagged code
14 flagged · loading sourcePackage contains a possible secret pattern.
dist/heart/daemon/cli-exec.jsView on unpkg · L3739Findings
Affected versions and remediation
This report applies to @ouro.bot/cli@0.1.0-alpha.829.
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.829 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.