OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security
TypeScript ai-securityapplication-securityclicode-scanningcodexcodex-securitycybersecuritydevsecopsnodejsnpmopenaisdksecuritytypescriptvulnerability-scanning
docs: run README CLI commands with npx (#945)
mluck-openai552f83d8f249
diff --git a/README.md b/README.mdindex 2d1306f29..9268655f8 100644--- a/README.md+++ b/README.md@@ -14,8 +14,8 @@ Requires Node.js 22.13.0 or later and Python 3.10 or later.```bashnpm install @openai/codex-security-codex-security login-codex-security scan /path/to/directory+npx @openai/codex-security login+npx @openai/codex-security scan /path/to/directory```For CI, set `OPENAI_API_KEY` instead of signing in.@@ -25,8 +25,8 @@ For CI, set `OPENAI_API_KEY` instead of signing in.Draft repository-wide or component-scoped `SECURITY.md` guidance for future scans:```bash-codex-security policy .-codex-security policy . --path services/api --knowledge-base architecture.md+npx @openai/codex-security policy .+npx @openai/codex-security policy . --path services/api --knowledge-base architecture.md```The command saves a draft outside the checkout; it does not install it or run a@@ -67,7 +67,7 @@ findings service, use the same scanner image with the## Findings service (preview)-Run `codex-security serve` to start the service without Docker. See+Run `npx @openai/codex-security serve` to start the service without Docker. See[running without Docker](sdk/typescript/README.md#running-without-docker)for prerequisites, credentials, and storage configuration.@@ -79,13 +79,13 @@ findings with pagination. Its read-only dashboard at `/dashboard` refreshes everfive seconds and shows stored findings and duplicate groups from the service'sdatabase. It also returns potential duplicates by embedding similarity within arepository or an explicit all-repository scope. The-`codex-security publish scan --to custom --findings-url http://localhost:3000`+`npx @openai/codex-security publish scan --to custom --findings-url http://localhost:3000`command uploads completed findings and their repository ID. The SDK and-`codex-security dedupe` command retrieve candidates, run independent Codex+`npx @openai/codex-security dedupe` command retrieve candidates, run independent Codexreviews locally, and persist accepted duplicate groups; `--all-repositories`opts into the broader scope.-Use `codex-security classify-severity --scan SCAN_ID --rubric /path/to/policy.md`+Use `npx @openai/codex-security classify-severity --scan SCAN_ID --rubric /path/to/policy.md`to assess selected findings under your own policy before publishing tickets.Scan classification checkpoints each finding in SQLite and reuses matchingassessments on reruns; `--reprocess` forces reassessment. The SDK exposes the same@@ -98,13 +98,13 @@ To use another inference provider, set its API key and select a model:```bashexport AWS_BEARER_TOKEN_BEDROCK="<your-bedrock-api-key>"export AWS_REGION="us-east-2"-codex-security scan . --provider amazon-bedrock --model openai.gpt-5.6-luna+npx @openai/codex-security scan . --provider amazon-bedrock --model openai.gpt-5.6-lunaexport OPENROUTER_API_KEY="<your-openrouter-api-key>"-codex-security scan . --provider openrouter --model anthropic/claude-sonnet-4.5+npx @openai/codex-security scan . --provider openrouter --model anthropic/claude-sonnet-4.5export FIREWORKS_API_KEY="<your-fireworks-api-key>"-codex-security scan . --provider fireworks --model accounts/fireworks/models/qwen3-235b-a22b+npx @openai/codex-security scan . --provider fireworks --model accounts/fireworks/models/qwen3-235b-a22b```## Documentation