consult-codex Audit report.

Warnings

• Permission surface may require sandboxing
• Financial research output is not financial advice; require human review before any live investment decision
• The skill instructs to use `dangerouslyDisableSandbox: true` for all codex calls, which disables the sandbox entirely, potentially allowing codex to access the full filesystem and network. The `-s read-only` flag may be ineffective when the sandbox is disabled, creating a contradiction and elevated risk.
• The skill does not explicitly warn the user about the implications of disabling the sandbox or provide guidance on verifying that the consultation is safe to run with full system access.
• Financial research output is not financial advice; require human review before any live investment decision.
• Quality score needs review
• Permission surface needs review: shell or command execution, filesystem or document access
• Stars/forks activity: 402 stars, 30 forks; issue activity unavailable in current metadata
• Permission surface: shell or command execution, filesystem or document access

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.