# openai/codex-security

> OpenAI's CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities in code, and for drafting SECURITY.md security policy.

- Magnitude: 2.1 out of 10 — Steady
- Stars: 11,252 total · +9 stars measured 2026-10-29, 00:09–07:52 UTC, ≈ 24 by evening
- Star trust: star growth looks organic
- Category: Security · Language: TypeScript · License: Apache-2.0 · Created: 2026-07-13 · Last push: 2026-10-29
- GitHub: https://github.com/openai/codex-security · Homepage: https://developers.openai.com/codex/security · Page: https://gitnova.dev/en/r/openai/codex-security

## Useful for

- Scan a directory for vulnerabilities with codex-security scan
- Generate a draft SECURITY.md for a repository via codex-security policy
- Embed security checks into CI using the SDK with OPENAI_API_KEY

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:09–07:52: 11243 → 11252 stars (+9). This is the change over that interval.
- Estimated end-of-day forecast: about +24 stars, using observed gains and the previous day.
- Over the last two days the pace is 1.9× that of the previous week and a half.
- Top new repositories in the last 4 months: #55.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 893
- Issues and pull requests: 2,106
- Watchers: 37
- Average over the last week: 15 per day
- Usual pace: 13 per day
- Stars in the last hour (measured): 1
- Latest release: action-v0.8.0 (2026-10-28)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 23, 13, 7, 7, 6, 12, 16, 27, 28, 14, 9, 8, 15, 16, 14, 8, 9, 6, 10, 8, 11, 21, 16, 8, 10, 14, 12, 17, 20, 9

## Magnitude by day, last 14 days

10-16 2.0, 10-17 2.2, 10-18 1.9, 10-19 2.2, 10-20 2.2, 10-21 1.9, 10-22 2.0, 10-23 1.9, 10-24 1.5, 10-25 1.7, 10-26 1.8, 10-27 1.8, 10-28 1.9, 10-29 2.1

## Spotted in now

- Top new repositories in the last 4 months: #55

## More in this category

1. **interplains/Zero-Breach-Toolkit** — 8.3 · Breakout · Security · Python · +245 stars measured 2026-10-29, 00:02–07:47 UTC, ≈ 1,150 by evening
   Free offline scanner for traces of known mercenary spyware (Pegasus, Predator, Graphite, Candiru) on Windows computers, Android phones and iPhone backups. Read-only, makes no network requests, and states the limits of every check.
   Full card: https://gitnova.dev/en/r/interplains/Zero-Breach-Toolkit.md
2. **KeygraphHQ/shannon** — 6.8 · Breakout · Security · TypeScript · +97 stars measured 2026-10-29, 00:03–07:47 UTC, ≈ 346 by evening
   Autonomous AI pentester for web applications and APIs: analyzes source code, finds attack vectors, and runs real exploits, reporting only vulnerabilities with a working proof-of-concept.
   Full card: https://gitnova.dev/en/r/KeygraphHQ/shannon.md
3. **vaishantsah/watson-AI-osint-all-in-one** — 5.3 · Early signal · Security · TypeScript · +2 stars measured 2026-10-29, 01:38–07:48 UTC, ≈ 70 by evening
   Free OSINT tool for Windows that searches profiles and mentions of a person by nickname, email, phone or website across 3,100+ public sources. No account or API keys required, results can be saved as PDF.
   Full card: https://gitnova.dev/en/r/vaishantsah/watson-AI-osint-all-in-one.md
4. **YuJunZhiXue/dsh-purge** — 5.3 · Peaking · Security · JavaScript · +365 stars measured 2026-10-29, 00:03–07:48 UTC, ≈ 1,090 by evening
   A local DeepSeek Harness plugin that reversibly patches installed @deepseek-ai packages to strip built-in refusals and swap prompts per model. Intended for red-team research and robustness evaluation in an authorized local environment.
   Full card: https://gitnova.dev/en/r/YuJunZhiXue/dsh-purge.md
5. **NVIDIA/SkillSpector** — 5.2 · Breakout · Security · Python · +119 stars measured 2026-10-29, 00:03–07:48 UTC, ≈ 361 by evening
   Security scanner for AI agent skills: detects vulnerabilities, malicious patterns, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before installation.
   Full card: https://gitnova.dev/en/r/NVIDIA/SkillSpector.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-29 07:59 UTC, updated every 30 minutes.