Ai Cli Safe Flags

✓ Guardrail AI Use Guardrails Experimental Devex Build And Ci

ai-use.ai-cli-safe-flags

Ensures AI CLI tools running in CI do not use dangerous permission-bypassing flags. Flags like --dangerously-skip-permissions (Claude), --yolo (Codex/Gemini), and --sandbox danger-full-access (Codex) remove safety guardrails.

ci safety dangerous flags permissions sandbox

Get Started View All AI Use Guardrails

Compatible Integrations

This guardrail works with the following integrations. Click to see how to use Ai Cli Safe Flags with each collector.

Ai Cli Safe Flags + AI Use Collector Provides AI usage metadata from repos and CI pipelines

→

Enable This Guardrail

Add the parent policy to your lunar-config.yml to enable this guardrail.

📄 lunar-config.yml

policies:
  - uses: github://earthly/lunar-lib/policies/ai-use@v1.0.0
    include: [ai-cli-safe-flags]
    # with: ...

How This Guardrail Works

This guardrail is part of the AI Use Guardrails policy. It evaluates data collected by integrations and produces a pass/fail check with actionable feedback.

When enabled, this check runs automatically on every PR and in AI coding workflows, providing real-time enforcement of your engineering standards.

Learn How Lunar Works →

↓ Integrations Gather Data

Collectors extract metadata from code, CI pipelines, tool outputs, and scans

{ } Centralized as JSON

All data merged into each component's unified metadata document

✓ This Guardrail Checks Current

Ai Cli Safe Flags runs and provides pass/fail feedback

Configuration Options

These inputs can be configured in your lunar-config.yml to customize how the parent policy (and this guardrail) behaves.

Input	Required	Default	Description
`canonical_filename`	Optional	`AGENTS.md`	The canonical (vendor-neutral) instruction filename
`required_symlinks`	Optional	`CLAUDE.md`	Comma-separated list of symlinks required alongside the canonical file
`min_lines`	Optional	`10`	Minimum number of lines for the root instruction file (0 to disable)
`max_lines`	Optional	`300`	Maximum number of lines for the root instruction file (0 to disable)
`max_total_bytes`	Optional	`32768`	Maximum combined bytes across all instruction files (0 to disable)
`required_sections`	Optional	`Project Overview,Build Commands`	Comma-separated required section heading substrings (case-insensitive)
`dangerous_flags_claude`	Optional	`--dangerously-skip-permissions,--allow-dangerously-skip-permissions`	Comma-separated dangerous flags for Claude CLI
`dangerous_flags_codex`	Optional	`--dangerously-bypass-approvals-and-sandbox,--yolo,--full-auto`	Comma-separated dangerous flags for Codex CLI
`dangerous_flags_gemini`	Optional	`--yolo,-y`	Comma-separated dangerous flags for Gemini CLI
`min_annotation_percentage`	Optional	`0`	Minimum percentage of commits that should have AI annotations (0 = awareness mode)

AI Use Guardrails

This guardrail is part of the AI Use Guardrails policy, which includes 9 guardrails for devex build and ci.

View Policy

Ready to Automate Your Standards?

See how Lunar can turn your engineering wiki, compliance docs, or postmortem action items into automated guardrails with our 100+ built-in guardrails.

Works with any process

Infrastructure conventions

Post-mortem action items

Security & compliance policies

Testing & quality requirements

Automate Now

Turn any process doc into guardrails

Book a Demo