Radar / AI security / Chainguard Harness
Chainguard Harness: frontier-model vulnerability hunting with verified fixes
Chainguard launched Harness, a service that uses Anthropic's Claude Mythos 5.1 to find exploitable vulnerabilities in a live, isolated build of an organization's application, delivering each verified finding with a recommended fix.
Why it matters
Frontier-model vulnerability discovery (previously limited to well-resourced critical-infrastructure teams) sold as an on-demand service with every finding verified and paired with a fix, purchasable through the Claude Marketplace.
What you could build with it
A seed-stage SaaS team with no dedicated security hire could point Harness at every release candidate and route verified findings-with-fixes into their normal pull-request review. The result: startup code reviewed to an enterprise security bar without hiring a security team.
Does it hold up?
Too early to judge: beta waitlist opened today; no independent reviews of finding quality or false-positive rates yet.
Learn more
First spotted on article: source.
More AI security
OpenAI, Anthropic and Google DeepMind jointly unveil cyber-focused safety models and safeguardsThe three rival labs disclosed weeks of behind-the-scenes coordination and jointly released a set of cyber-focused AI…security · JEV 0.73OpenAI textGrain watermarking for ChatGPT and Codex in the EUOpenAI will roll out its invisible textGrain watermarking system to ChatGPT/Codex users in the EU over the coming…security · JEV 0.65Cloudflare security-audit-skill: multi-phase security audits for coding agentsA coding-agent skill that runs multi-phase security audits with independently verified, machine-checkable findings.security · JEV 0.63LiveNerf: a pre-registered benchmark for post-release model driftOpen-source, pre-registered 30-day benchmark that detects whether Claude Opus 5.5 quietly gets worse after launch.security · JEV 0.61Sandlock 0.8.8: deferred commit for agent sandboxesThe process-based Linux AI sandbox (no container, no VM) ships deferred commit: every run returns a changeset of what…security · JEV 0.58Microsoft Execution Containers (MXC) goes GA on Windows 11At its Oct 7 Windows AI event with NVIDIA, Microsoft announced general availability of Microsoft Execution Containers…security · JEV 0.58
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.