Radar / AI security / Codex Security 0.10.0
Codex Security 0.10.0: OpenAI's agentic vulnerability scanner adds resumable scans and cost budgets
OpenAI released Codex Security 0.10.0 on 12 Nov 2026: the open-source CLI and TypeScript SDK that builds a threat model, validates vulnerabilities in a sandbox and generates fixes now resumes interrupted scans from checkpoints, caps bulk-scan spend with a shared cost budget, and imports ArmorCode SAST findings.
Why it matters
An agentic scanner that validates each finding before reporting it - OpenAI reports a 0.81% false-positive rate - now with resumable scans and a cost ceiling for bulk runs.
What you could build with it
An indie security consultant could run Codex Security across a client's repositories before every release, turning the findings into a fixed-price audit report with verified fixes, and charge per audit instead of per hour.
Does it hold up?
Usable with caveats - the CLI is free and open source and runs in CI, but scanning needs an OpenAI account, costs $1.46-$8.54 per small-repo scan in independent testing, and some features still require beta access.
Built with Codex Security 0.10.0
- OpenAI's Daybreak adds 2 tools to fix flawsdailyagentic.info · Daybreak launch context: Codex Security 0.10.0 shipped 12 Nov alongside Daybreak Red Team and Defense Factory.
- Daybreak Defense Factory: OpenAI Code Security (2026)explainx.ai · Explains how Codex Security fits under Daybreak as the open-source CLI layer beneath the managed Defense Factory.
- OpenAI turns defense factory into Cloud productstartuphub.ai · Coverage of the Daybreak expansion and the Codex Security Cloud scanning GitHub repos on every commit.
Learn more
First spotted on article: source.
More AI security
NVIDIA SkillSpector: security scanner for AI agent skills, trending againNVIDIA's open-source SkillSpector scanner is trending on GitHub today: it audits AI agent skills before installation…security · JEV 0.75Cloudflare security-audit-skill: turn your coding agent into a security auditorA coding-agent skill for multi-phase security audits with independently verified, machine-readable findings.security · JEV 0.72Shannon: open-source AI pentester that reports only vulnerabilities it can actually exploitCLI agent that combines source-code analysis with live exploitation against web apps and APIs under a 'no exploit, no…security · JEV 0.71AiSOC: open-source AI security operations center with agent triageSelf-hosted SOC that fuses alerts into incidents and hands them to LLM agents that record every prompt and tool call…security · JEV 0.71iFixAi: independent auditing of AI agents in under 120 secondsiFixAi audits whether an AI agent is doing what it is supposed to do, run by a human or by the agent itself, answering…security · JEV 0.68NVIDIA OpenShell joins CNCF: open governance for securing autonomous agentsNVIDIA contributed OpenShell, its open-source runtime for securing and governing autonomous agents, to the CNCF as a…security · JEV 0.68
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.