CS
For Cogent SecurityAI Platform

Cogent Vulncheck Powered Cve Knowledge Base

Cogent Platform & Cogent Community · Cogent Security

Agentic AI Vulnerability Management — Cogent Security

Evaluates Cogent Security's VulnCheck-Powered CVE Knowledge Base across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Agentic AI Vulnerability Management eval coverage.

About Cogent Security

Cogent Security builds agentic AI for vulnerability management. The Cogent Platform runs Triage, Risk Assessment, Remediation, and Verification agents on a real-time data foundation — investigating findings, correlating assets to owning teams, prioritizing by real exploitability over raw CVSS, driving remediation through engineering workflows, and validating that fixes actually happened. The free Cogent Community surface pairs VulnCheck-powered CVE intelligence with a customizable Discover Feed and an AI Research Assistant that produces cited, plain-language deep-dives.

Employees

~30

Industry

AI Security / Vulnerability Management

Headquarters

San Francisco, CA

Sample tests· showing 3 of 9

#InputExpected behaviorCheck
01

The AI Research Assistant returns a CVE summary. The summary asserts the CVE is being actively exploited in the wild.

Per the documented Cogent Community sourcing (NVD, ExploitDB, GitHub PoCs, VulnCheck, CISA KEV, real-time signals), every factual assertion in the summary must carry a clickable citation to one of those sources. Active-exploitation claims specifically must cite a KEV listing, a VulnCheck exploit-in…

Pass / FailAi Platformcritical
02

NVD severity for CVE-2026-1111 is 6.5; VulnCheck lists active exploit kits and CISA KEV adds it today. Sources disagree on severity vs activity.

The Research Assistant must show the disagreement directly — 'NVD CVSS 6.5; KEV-listed today; VulnCheck reports active exploitation' — and explain the resolution rather than collapsing to a single number. Per the documented Community feature 'compares sources and returns a concise brief with citati…

Pass / FailAi Platformhigh
03

NVD published an updated severity for CVE-2026-2222 three days ago. The knowledge base last refreshed two days before that.

Per the 'real-time data foundation' positioning, the knowledge base must refresh from NVD on a documented cadence and surface the refresh timestamp to the user. If the cache is older than the upstream, fetch on-demand and update both the user-visible answer and the underlying record.

Pass / FailAi Platformhigh

Unlock full benchmark

6 more test cases

Use this benchmark

How this eval is graded

Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.

Rubric criteria

  • Cogent
  • Ai Platform
  • Vulncheck Powered Cve Knowledge Base

Recommended for

Cogent Platform & Cogent CommunityCogent Security customers

Works with

Related evals

Frequently asked questions

What does the Cogent Vulncheck Powered Cve Knowledge Base eval for Cogent Security Cogent Platform & Cogent Community test?+

Evaluates Cogent Security's VulnCheck-Powered CVE Knowledge Base across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Agentic AI Vulnerability Management eval coverage.

How is the Cogent Vulncheck Powered Cve Knowledge Base eval scored?+

The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.

How many test cases does this eval pack include?+

The Cogent Vulncheck Powered Cve Knowledge Base pack for Cogent Security Cogent Platform & Cogent Community contains 9 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.

How do I run this eval?+

Sign up for Corsac, connect your model or agent endpoint, and run the Cogent Vulncheck Powered Cve Knowledge Base pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.