Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Containers
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Skills
  • Learn
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)
All skills
Code

Audit your infrastructure code

The misconfigurations that actually reach production, ranked by blast radius.

Fill it in

Where the Terraform or manifests live.

Not by scanner severity.

The actual diff, not a description.

Your prompt

Audit the infrastructure code in [the repo].

Look for what actually reaches production: a security group open to the world, an
unencrypted bucket, an over-permissive role, public snapshots, and logging that
was never turned on. Those are the ones that appear in breach reports; the rest of
a scanner's output is noise around them.

Rank by BLAST RADIUS, not by scanner severity. A medium finding on the role your
CI assumes is worse than a high on a sandbox, and severity labels cannot see that
difference.

Write the fixes as a diff. A finding with a remediation paragraph gets read; one
with a patch gets merged.
Say which findings are accepted risk rather than mistakes, if the code suggests
somebody decided deliberately.
Use Audit your infrastructure codeOpens with everything above already filled in.

Why this works

Scanner severity cannot see blast radius: a medium finding on the role your CI assumes is worse than a high on a sandbox. This ranks by what an attacker reaches and writes the fixes as a diff, because a finding with a patch gets merged.

More code skills

  • idapt Code
  • Fix a failing test

Use it now in a chat in 1 click

Use Audit your infrastructure code
Fix a GitHub issue
  • Find security bugs
  • Ship a feature
  • Speed up slow code