@ouro.bot/cli@0.1.0-alpha.891
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 12d ago · by lpm-firewall-aiThe inspected code supports user-triggered plugin installation and agent extension capability, which warrants a warning under the agent integration policy. Source inspection did not substantiate the scanner’s stronger claims of credential exfiltration or persistence as an attack.
Decision evidence
public snapshot- The package exposes CLI entrypoints and declares no npm install lifecycle hook.
- Plugin installation is a CLI operation that clones a requested source into the plugin directory; enabled plugins can supply MCP servers.
- Provider credentials are read from local auth files or sent to their intended provider endpoints.
- The version manager can install a requested CLI version at runtime.
- The inspected auth flow uses the GitHub API for Copilot endpoint discovery and reads Codex tokens from the local Codex auth file.
- No inspected source established covert credential exfiltration or an unconsented install-time agent configuration change.
Source & flagged code
16 flagged · loading sourcePackage contains a possible secret pattern.
dist/heart/daemon/cli-exec.jsView on unpkg · L3741Findings
Affected versions and remediation
This report applies to @ouro.bot/cli@0.1.0-alpha.891.
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.891 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.