@ouro.bot/cli@0.1.0-alpha.920
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 9d ago · by lpm-firewall-aiSource inspection found no install hook or concrete malicious behavior. The flagged credential flows use provider-aligned destinations, and agent integration changes occur through explicit setup flows.
Decision evidence
public snapshot- The manifest identifies CLI entrypoints and contains build and packaging scripts; the reviewed excerpts show no install lifecycle action or same-package dependency.
- Authentication reads local Codex credentials or obtains GitHub CLI credentials, checks Copilot access at GitHub, then stores the selected provider credentials for the agent.
- Agent integration writes Claude Code MCP and hook settings only in the explicit setup command path; the clone flow asks before starting that setup.
- Plugin installation derives a local plugin directory from the supplied source and performs installation through its CLI handler.
- The reviewed helper code covers local process execution, version cleanup, and agent-scoped trust-file operations; these excerpts establish no unrelated credential recipient or automatic install-time mutation.
Source & flagged code
16 flagged · loading sourceThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/heart/daemon/cli-exec.jsView on unpkgPackage contains a possible secret pattern.
dist/heart/daemon/cli-exec.jsFindings
Affected versions and remediation
This report applies to @ouro.bot/cli@0.1.0-alpha.920.
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.920 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.