CSCIO Shortlist
70
of 100

AI Security

Giskard

Giskard · Vendor site

Open-core AI red teaming and evaluation for AI agents and LLM applications.

What it does

  • Open-source Python library for local agent testing
  • Automated vulnerability scans with 50+ adversarial probes (Professional)
  • Domain-specific evaluation datasets and RAG metrics
  • Human-in-the-loop review, CI/CD integration, alerting

Best fit

Teams that want to start testing free and upgrade to continuous red teaming for production agents.

Watch-outs

Testing and evaluation focus; not a governance register.

Deployment

Open-source local; Professional on-premise, private cloud, or SaaS (per pricing page).

Notable integrations

  • CI/CD (SDK)
  • Bring-your-own LLMs
  • SSO / RBAC

Frameworks referenced by the vendor

  • OWASP

Pricing

Open-source tier free; Professional via sales (pricing page lists features, not prices).

Sources

Facts above come from the vendor's own public pages. Vendor claims (such as analyst recognitions) are attributed and not independently verified. Spot an error? Email editors@cioshortlist.com.