@ouro.bot/cli@0.1.0-alpha.816
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 inspected risk is first-party agent setup that persists user-level hooks after an explicit command, so it warrants a warning. No npm install hook or concrete attack behavior was established.
Decision evidence
public snapshot- package.json exposes CLI entrypoints and has no install lifecycle hook; setup is an explicit command requiring a tool and agent.
- That setup registers a user-level Claude Code MCP server and writes persistent Claude hooks that run on session start, stop, and selected tool use.
- Plugin installation clones a supplied source and can enable it for a named agent when requested.
- The inspected credential paths collect provider credentials for storage and send GitHub Copilot tokens to api.github.com; no unrelated credential recipient was found.
- The agent setup and plugin installation behavior is reached through explicit CLI commands, not an npm install hook.
- The reviewed source did not establish credential theft, destructive behavior, or another concrete attack.
Source & flagged code
13 flagged · loading sourcePackage contains a possible secret pattern.
dist/heart/daemon/cli-exec.jsView on unpkg · L3739Package source references child process execution.
dist/heart/auth/auth-flow.jsView on unpkg · L42Findings
Affected versions and remediation
This report applies to @ouro.bot/cli@0.1.0-alpha.816.
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.816 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.