@ouro.bot/cli@0.1.0-alpha.894
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 behavior supports a guarded, operator-invoked agent extension capability, not an active attack. The scanner’s higher-risk claims are not established by the inspected excerpts, so this warrants a warning rather than a block.
Decision evidence
public snapshot- The package has no npm install lifecycle hook; its published entrypoints are CLI programs.
- The agent plugin installer runs from an explicit command, installs a plugin into the package-managed plugins directory, and can enable it for a named agent.
- The plugin command can clone a repository and place its selected subpath in the plugin directory.
- Codex authentication reads the existing local auth.json and sends its token to GitHub’s Copilot endpoint for endpoint discovery.
- The flagged CLI configuration excerpt selects the local Claude configuration directory; the cited changelog excerpt describes MCP configuration parsing.
- The inspected sources do not establish an unconsented install-time agent configuration mutation, credential theft, or command-output exfiltration. The observed plugin setup is an operator-invoked capability.
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.894.
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.894 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.