Eval directory
Evals for Mend.io
4 evaluation packs covering adversarial robustness, safety gates, workflow quality, and operator-level checks for Mend.io AI products.
Available eval packs for Mend.io
4 packs ready to run.
Adversarial Security Validation V1
Prompt InjectionToxicityAdversarial eval for prompt injection resistance, tool abuse detection, false positive pressure handling, and evasion technique detection in AppSec workflows.
Expert Safety Gate Eval V1
Task CompletionSafety-gate eval for blocking unsafe AI fixes, enforcing escalation discipline for zero-days and supply chain attacks, maintaining policy boundaries, and protecting code integrity.
Power User Ops Eval V1
Task CompletionOperator-facing eval focused on evidence traceability, handoff quality, noise discipline, and workflow automation for AppSec operations.
Workflow Painpoint Eval V1
Task CompletionBuyer-facing workflow eval covering AI remediation quality, AI component inventory gaps, system prompt hardening impact, transitive dependency complexity, and cross-scan correlation pain points.
Why eval Mend.io AI
Mend.io'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 Mend.io 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 Mend.io's public product surface and runnable in Corsac with your own data.