feat(cli): add optional patch-risk assessment to deterministic reviews

README.md

@@ -23,7 +23,7 @@ npx @openai/codex-security scan .
 npx @openai/codex-security scan . --patch
 npx @openai/codex-security scan . --patch --patch-severity high --json
 npx @openai/codex-security scan . --patch --patch-severity high --create-pr
-npx @openai/codex-security scan . --patch --review-minimality --review-style
+npx @openai/codex-security scan . --patch --review-minimality --review-style --assess-patch-risk
 npx @openai/codex-security scan . --model gpt-5.6-terra --effort high
 npx @openai/codex-security scan . --scan-prompt-file scan.md --post-scan-prompt-file follow-up.md
 npx @openai/codex-security scan . --validation-prompt-file validation.md
@@ -48,10 +48,12 @@ Use `--patch --patch-severity high` to fix high and critical findings. Add
 verified files and open a draft GitHub pull request. Ordinary scans do not
 change repository files.
 
-Add `--review-minimality` or `--review-style` to `scan --patch` or `patch`
-to trigger a deterministic review workflow. The CLI runs each selected review
-as a separate, independent, read-only model invocation: minimality first, then
-local coding style. Both reviews are optional and disabled by default.
+Add `--review-minimality`, `--review-style`, or `--assess-patch-risk` to
+`scan --patch` or `patch` to trigger a deterministic review workflow. The CLI
+runs each selected review as a separate, independent, read-only model invocation:
+minimality first, then local coding style, then patch-risk assessment. Each
+review is optional and disabled by default; risk assessment never merges a pull
+request.
 Set `--max-review-revisions 5` to allow up to five author revisions across
 actionable review findings; later-stage revisions restart earlier reviews, and
 blocked reviews still stop immediately.

sdk/typescript/README.md

@@ -252,7 +252,7 @@ npx @openai/codex-security scan /path/to/repository --headless
 npx @openai/codex-security scan /path/to/repository --patch
 npx @openai/codex-security scan /path/to/repository --patch --patch-severity high --json
 npx @openai/codex-security scan /path/to/repository --patch --patch-severity high --create-pr
-npx @openai/codex-security scan /path/to/repository --patch --review-minimality --review-style
+npx @openai/codex-security scan /path/to/repository --patch --review-minimality --review-style --assess-patch-risk
 npx @openai/codex-security scan /path/to/repository --model gpt-5.6-terra
 npx @openai/codex-security scan /path/to/repository --model gpt-5.6-terra --effort high
 npx @openai/codex-security scan /path/to/repository --path src --path tests
@@ -306,7 +306,7 @@ npx @openai/codex-security patch "Missing authorization check" --effort high
 npx @openai/codex-security patch OCCURRENCE_ID
 npx @openai/codex-security patch --scan SCAN_ID --severity high --json
 npx @openai/codex-security patch --scan SCAN_ID --severity high --create-pr
-npx @openai/codex-security patch --scan SCAN_ID --review-minimality --review-style
+npx @openai/codex-security patch --scan SCAN_ID --review-minimality --review-style --assess-patch-risk
 npx @openai/codex-security patch --resume-pr codex-security/patch-SCAN_ID
 npx @openai/codex-security patch --scan latest --severity medium
 npx @openai/codex-security patch --linear-issue SEC-123 --linear-issue SEC-124
@@ -505,16 +505,19 @@ saved-finding `patch` command to commit only verified patch files and open a
 draft pull request with `gh`. If the push or pull request fails, run the printed
 `patch --resume-pr BRANCH` command from the same repository. It uses the saved
 commit without running Codex again and refuses to publish if the branch changed.
-Add `--review-minimality` or `--review-style` to either patching workflow
-to trigger a deterministic review workflow. The CLI runs each selected stage
-as a separate, independent, read-only model invocation, in minimality-then-style
-order. Minimality review removes unnecessary or unrelated changes; style review
-checks project instructions, local conventions, and applicable style guides.
-Both stages are disabled by default.
+Add `--review-minimality`, `--review-style`, or `--assess-patch-risk` to either
+patching workflow to trigger a deterministic review workflow. The CLI runs each
+selected stage as a separate, independent, read-only model invocation, in
+minimality-then-style-then-risk order. Minimality review removes unnecessary or
+unrelated changes; style review checks project instructions, local conventions,
+and applicable style guides; final risk assessment examines applicability, blast
+radius, regression protection, and merge risk without merging the patch. Each
+stage is disabled by default.
 Set `--max-review-revisions 5` to allow up to five author revisions across the
-selected review stages. After a later-stage revision, earlier selected reviews
-run again; blocked reviews still stop immediately. Without this option,
-minimality and style each permit one revision.
+selected review stages, including actionable risk-assessment findings. After a
+later-stage revision, earlier selected reviews run again; blocked reviews still
+stop immediately. Without this option, minimality and style each permit one
+revision, and risk-assessment findings are not revised.
 JSON scan results include `patchSeverity`. Scan and
 saved-finding results include one `patches` entry per selected finding with
 status `verified`, `no_change`, `blocked`, or `failed`, plus `pullRequest` when

sdk/typescript/_bundled_plugin/references/scan-artifacts.md

@@ -110,6 +110,7 @@ Standard scans and Deep Standard scan workers include attack-path analysis direc
 ## Fix Finding Paths
 
 - Fix report, when using an existing scan artifact directory: `<artifacts_dir>/fix_report.md`
+- Patch risk assessment, when requested for a remediation patch: `<artifacts_dir>/patch-risk-assessment.json`
 
 ## Placement Rules