👀79
🔥86
Chainguard ships three agent-security products: Harness runs Claude Mythos 5.1 vulnerability hunts for you, Checks turns CI into an agent-callable pre-commit check, Workspaces adds microVM sandboxes
On 2026-10-14 Chainguard launched Harness, Checks, and Workspaces. Harness has Chainguard staff run Claude Mythos 5.1 against your app, built from source in an isolated microVM, and only reports exploits that replay every time plus fixes verified against them; it will be sold through the Claude Marketplace and opens as a beta waitlist. Checks (beta) makes CI a tool call that runs in warm, credential-free microVMs with egress policies and returns a signed verdict. Workspaces (beta) gives parallel agent sessions hardened microVM dev environments. Both betas come with a 30-day free trial.
Key Takeaways
- Harness: Chainguard staff operate Claude Mythos 5.1, so customers need no model access; an exploit only makes the report if it replays every time in a fresh microVM, each fix must make it fail, and a named engineer signs off
- Harness will be purchasable on the Claude Marketplace against existing Anthropic commitments; limited beta waitlist for now (per Chainguard)
- Checks beta: config in
.chainguard/ci/*.yaml, drafts generated from existing GitHub Actions viachainctl; runners hold no credentials, a host-side proxy injects short-lived ones in flight - Workspaces beta:
chainctl developopens a remote microVM; while waiting on a developer it stays live 10 minutes, then snapshots and stops compute - Both Checks and Workspaces have a 30-day free trial; Chainguard published no speed or detection-rate numbers
Linked Models & Agents:
