monizb/Security PR Reviewer
Security-focused PR reviewer with data-flow highlights powered by Gemini.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| gemini_api_key | Google Gemini API key (or set env GEMINI_API_KEY) | yes | — |
| model | Gemini model name | no | gemini-1.5-pro-latest |
| temperature | Sampling temperature | no | 0.2 |
| max_output_tokens | Max output tokens from Gemini | no | 4096 |
| enable_inline | Emit inline review suggestions JSON via output | no | false |
| personality | Reviewer tone/persona for LLM prompt | no | mentor, concise, slightly witty |
| update_existing | Update existing bot comment instead of creating a new one | no | true |
| fail_on_high | Fail the job if High or Critical risk findings are detected | no | false |
| repo | Optional repo in owner/name for manual invocation | no | — |
| owner | Optional owner; overrides repo owner | no | — |
| pr_number | Optional pull request number for manual invocation | no | — |
Outputs
| name | description |
|---|---|
| comment_id | The GitHub comment id that was created/updated. |
| risk | Overall risk level (None|Low|Medium|High|Critical). |
| inline | JSON array string of suggested inline comments. |
| summary_url | URL of the summary comment. |