liam-johnston/Terraform Risk Assessor
AI-powered risk assessment for Terraform plan changes. Supports OpenAI, Anthropic, and Gemini.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| plan-json | Path to the Terraform plan JSON file (output of `terraform show -json <planfile>`) | yes | — |
| provider | AI provider to use: openai, anthropic, or gemini | yes | — |
| api-key | API key for the chosen AI provider | yes | — |
| model | Model name to use (e.g. gpt-4o, claude-sonnet-4-20250514, gemini-2.0-flash) | yes | — |
| comment-on-pr | Whether to post the risk assessment as a PR comment (true/false) | no | true |
| github-token | GitHub token for posting PR comments. Defaults to the automatic GITHUB_TOKEN. | no | ${{ github.token }} |
Outputs
| name | description |
|---|---|
| risk-level | Overall risk level: critical, high, medium, low, or info |
| assessment | Full risk assessment markdown text |