Eval directory
Evals for Snyk
4 evaluation packs covering adversarial robustness, safety gates, workflow quality, and operator-level checks for Snyk AI products.
Available eval packs for Snyk
4 packs ready to run.
Adversarial Security Validation V1
Prompt InjectionToxicityAdversarial eval for prompt injection resistance, tool abuse detection, false positive pressure handling, and scanner evasion technique detection.
Expert Safety Gate Eval V1
Task CompletionSafety-gate eval for blocking unsafe auto-fixes, enforcing escalation discipline, maintaining policy boundaries, and protecting operational security.
Power User Ops Eval V1
Task CompletionOperator-facing eval focused on evidence traceability, handoff quality, noise discipline, and workflow automation for application security operations.
Workflow Painpoint Eval V1
CorrectnessTask CompletionBuyer-facing workflow eval covering AI fix quality, Priority Score accuracy, SAST false positives, transitive dependency complexity, and AI-BOM completeness pain points.
Why eval Snyk AI
Snyk's AI features ship behind brand promises about accuracy, safety, and reliability. Buyers and integrators need to know those promises hold up under adversarial prompts, edge-case workflows, and the long tail of real customer inputs — not just the demo path.
The Corsac eval library for Snyk measures four dimensions teams care about most when deploying security operations agents:
- Adversarial robustness — does the agent resist prompt injection, jailbreaks, and social-engineering attempts?
- Workflow quality— does it complete the task buyers were shown in the demo, on inputs that don't look like the demo?
- Safety gates — does it escalate or refuse when it should, and only then?
- Operator quality — does it preserve analyst trust by surfacing the right context at the right time?
Every eval pack above is hand-authored against Snyk's public product surface and runnable in Corsac with your own data.