{
 "name": "Use-Case Matrix",
 "edition": "2026-11-19",
 "license": "CC BY 4.0",
 "cite": "Agentic AI in Cybersecurity, Use-Case Matrix, edition 19 Nov 2026, https://agenticaiincybersecurity.com/use-cases/",
 "fields": [
  "Job",
  "What an agent reads",
  "What it does without a person",
  "Where a person approves",
  "What evidence it leaves",
  "Vendors that publish an agent",
  "Agents named (vendor: agent)",
  "Sources",
  "Read"
 ],
 "rows": [
  {
   "Job": "Vulnerability triage and remediation",
   "What an agent reads": "Published agents read scanner findings and how the vulnerable component is used in the customer's code or environment (usage, reachability, exposure, ownership).",
   "What it does without a person": "Vendors describe agents that rank or dismiss findings with a stated reason and, in some products, draft tickets or fixes. Which actions run unattended is a setting in several products, not a fixed behavior.",
   "Where a person approves": "Vendors describe an approval step before changes: configurable per action, an approval queue, or review and merge of a pull request. The point where approval sits differs by product.",
   "What evidence it leaves": "Vendors describe logs of agent steps and decisions, with reasons attached to each decision.",
   "Vendors that publish an agent": "Aikido; Amplify Security; Astelia; Averlon; Backline; Checkmarx; Cogent Security; Corridor; CrowdStrike; Cycode; Dux Security; Endor Labs; GitHub; Maze; Microsoft; Onit Security; Pixee; ProjectDiscovery; Qualys; Rival Security; Seemplicity; Semgrep; Snyk; Tenable; Torq; Vicarius; Wiz; Zafran",
   "Agents named (vendor: agent)": "Aikido: Aikido Agent (CVE Exploitability Analysis); Amplify Security: Amplify Console triage and remediation agents; Astelia: The Investigator (Automated Triage); Astelia: The Fixer (Agentic Remediation); Averlon: Mitigation Agents; Backline: Andy (Analyst); Backline: Polly (Planner); Backline: Vera (Verifier); Checkmarx: Triage Assist; Cogent Security: Cogent AI agents (vulnerability lifecycle); Corridor: Corridor Agent; CrowdStrike: Exposure Prioritization Agent (Charlotte AI, Falcon Exposure Management); Cycode: Exploitability Agent; Dux Security: Dux AI agents; Endor Labs: AI SAST Remediation (AURI Agent); GitHub: Assign security campaign alerts to Copilot; Maze: Maze remediation agents; Microsoft: Vulnerability Remediation Agent (Security Copilot in Intune, public preview); Onit Security: Exploitability Agent; Onit Security: Ownership Agent; Onit Security: Remediation Agent; Onit Security: Mitigation Agent; Pixee: Pixee triage engine (AI agents tier); ProjectDiscovery: Vuln Triage Agent (Neo); ProjectDiscovery: Verification Agent (Neo); Qualys: Agent Val; Qualys: Agent Sara; Rival Security: Triage findings; Seemplicity: Host VM Analyst; Semgrep: Semgrep Multimodal (formerly Semgrep Assistant); Semgrep: Semgrep Agentic Workflows (review step); Snyk: Evo Remediation Agent; Tenable: Tenable Hexa AI; Torq: Torq agentic AI in vulnerability management (HyperAgents); Vicarius: Agentic Exploit Simulation (vIntelligence); Wiz: Green Agent; Zafran: Agentic Remediation",
   "Sources": "https://help.aikido.dev/aikido-agent/cve-exploitability-analysis.md https://www.astelia.io/use-cases/deploy-astelia-agents https://www.endorlabs.com/platform/agentic-workflows https://www.crowdstrike.com/en-us/platform/exposure-management/ https://www.cogent.com/ai/cogent-ai-engine https://mazehq.com/solutions/remediation https://www.wiz.io/blog/introducing-wiz-green-agent https://genai.owasp.org/llmrisk/llm062025-excessive-agency/ https://www.crowdstrike.com/en-us/platform/charlotte-ai/ https://www.astelia.io/post/closing-the-exposure-loop https://www.wiz.io/blog/introducing-wiz-agents https://artificialintelligenceact.eu/article/14/ https://www.cogent.com/platform/cyber-defense-factory https://github.com/mitre-atlas/atlas-data/blob/main/dist/ATLAS.yaml",
   "Read": "2026-11-19"
  },
  {
   "Job": "Response to a new disclosure",
   "What an agent reads": "Published agents read the new advisory against the customer's software inventory, SBOMs and asset data, sometimes before scanner signatures exist.",
   "What it does without a person": "Vendors describe agents that match a disclosure to assets and hand back a short list of affected systems with next steps. Some also generate detection or mitigation scripts.",
   "Where a person approves": "Vendors describe approval before mitigation reaches live assets: a publish step, an approval gate, or sign-off thresholds.",
   "What evidence it leaves": "Vendors describe execution or audit logs of the match and the conclusions reached.",
   "Vendors that publish an agent": "Astelia; Cogent Security; Endor Labs; Maze; Onit Security; Qualys; Rival Security; Seemplicity; Vicarius; Zafran",
   "Agents named (vendor: agent)": "Astelia: The Hunter (Zero-Day Detection); Cogent Security: Cogent AI agents (new disclosure); Endor Labs: Malware Responder (AURI Agent); Maze: Maze Cloud agents; Onit Security: Zero-Day Agent; Qualys: Agent Insta; Qualys: Agent Nyra; Rival Security: 0-day response; Seemplicity: SCA Analyst; Vicarius: ScriptAI; Zafran: Zero Day Agent",
   "Sources": "https://www.astelia.io/use-cases/deploy-astelia-agents https://www.cogent.com/ https://www.zafran.io/ https://seemplicity.ai/news/ai-analysts-autonomous-vulnerability-response/ https://onit.security/blog/zero-day-response/ https://www.qualys.com/apps/agentic-ai https://www.vicarius.io/features/scriptai https://mazehq.com/platform/cloud https://genai.owasp.org/llmrisk/llm062025-excessive-agency/ https://onit.security/platform/ https://www.cogent.com/ai/cogent-ai-engine https://www.zafran.io/platform https://www.qualys.com/apps/trurisk-eliminate/ https://artificialintelligenceact.eu/article/14/ https://www.astelia.io/post/closing-the-exposure-loop https://onit.security/blog/ai-agents-vulnerability-management/ https://www.cogent.com/platform/cyber-defense-factory https://github.com/mitre-atlas/atlas-data/blob/main/dist/ATLAS.yaml",
   "Read": "2026-11-19"
  },
  {
   "Job": "Code and dependency fixes",
   "What an agent reads": "Published agents read the finding, the repository source, dependency manifests and build or test results.",
   "What it does without a person": "Vendors describe agents that explore the code, generate a fix, validate it (build, tests) and open a pull request or merge request.",
   "Where a person approves": "Vendors describe a human review and merge step on the pull request, and in some products an approval before any file edit or branch push.",
   "What evidence it leaves": "Vendors describe the pull request itself as the record, plus agent logs and audit trails in some products.",
   "Vendors that publish an agent": "Aikido; Averlon; Backline; Checkmarx; Corridor; Cycode; Endor Labs; GitHub; Google; Maze; Mobb; Pixee; Rival Security; Seemplicity; Semgrep; Snyk",
   "Agents named (vendor: agent)": "Aikido: Aikido Agent and AutoFix; Averlon: Remediation Agents; Backline: Codie (Coder); Checkmarx: Remediation Assist; Checkmarx: Developer Assist; Corridor: Corridor Agent (fixes); Cycode: Fix & Remediation Agent; Endor Labs: SCA Remediation (AURI Agent); GitHub: Agentic autofix for code scanning; GitHub: Copilot Autofix; GitHub: Copilot assigned to Dependabot alerts; Google: CodeMender; Maze: Maze Code agents; Mobb: Mobb AI Agent; Pixee: Pixee fix generation; Rival Security: Auto-remediate; Rival Security: Dependency audit; Seemplicity: SAST Analyst; Semgrep: Semgrep Agentic Workflows (fix step); Snyk: Evo Remediation Agent (dependency fixes)",
   "Sources": "https://www.endorlabs.com/platform/agentic-workflows https://docs.github.com/en/code-security/concepts/code-scanning/autofix-for-code-scanning https://backline.ai/ https://semgrep.dev/products/semgrep-agentic-workflows/ https://snyk.io/news/snyk-launches-evo-agentic-appsec/ https://rival.security/ https://www.anthropic.com/engineering/building-effective-agents https://docs.semgrep.dev/semgrep-code/triage-remediation/autofix.md https://deepmind.google/discover/blog/introducing-codemender-an-ai-agent-for-code-security/ https://www.endorlabs.com/solutions/agentic-remediation https://checkmarx.com/press-releases/checkmarx-unveils-self-healing-application-security-in-assist-agent-family/ https://rival.security/use-cases https://seemplicity.ai/news/response-options/ https://genai.owasp.org/llmrisk/llm062025-excessive-agency/ https://artificialintelligenceact.eu/article/14/ https://docs.github.com/en/code-security/dependabot/dependabot-alerts/about-dependabot-alerts https://backline.ai/product/ https://snyk.io/evo/agentic-appsec/ https://docs.pixee.ai/enterprise/compliance https://github.com/mitre-atlas/atlas-data/blob/main/dist/ATLAS.yaml",
   "Read": "2026-11-19"
  },
  {
   "Job": "Cloud posture",
   "What an agent reads": "Published agents read cloud configuration findings, resource metadata, and in some products infrastructure-as-code changes.",
   "What it does without a person": "Vendors describe agents that enrich alerts, rank misconfigurations and generate fixes; Wiz describes automatic remediation for high-confidence verdicts, and Prowler's assistant is read-only guidance.",
   "Where a person approves": "Vendors describe routing lower-confidence or high-impact remediation to a person, or running fixes through the customer's change process.",
   "What evidence it leaves": "Vendors describe an investigation view, recorded reasoning for each action, or a retained decision record.",
   "Vendors that publish an agent": "Averlon; Prowler; Rival Security; Sysdig; Tamnoon; Upwind; Wiz",
   "Agents named (vendor: agent)": "Averlon: Infrastructure Risk PreCog Agent; Prowler: Prowler Lighthouse AI; Rival Security: Cloud posture; Sysdig: Posture agent (Sysdig Agentic AI); Tamnoon: Tami; Upwind: Green; Wiz: Green Agent (cloud misconfiguration remediation)",
   "Sources": "https://www.tamnoon.io/product https://www.averlon.ai/blog/automating-remediation-application-infrastructure-security-issues https://www.upwind.io/agentic-security https://www.wiz.io/blog/introducing-wiz-agents https://www.sysdig.com/products/agentic-ai https://prowler.com/lighthouse-ai https://genai.owasp.org/llmrisk/llm062025-excessive-agency/ https://tamnoon.io/ https://artificialintelligenceact.eu/article/14/ https://www.wiz.io/blog/introducing-wiz-green-agent https://github.com/mitre-atlas/atlas-data/blob/main/dist/ATLAS.yaml",
   "Read": "2026-11-19"
  },
  {
   "Job": "Threat modeling",
   "What an agent reads": "Published agents read design documents, diagrams, text prompts or the repository.",
   "What it does without a person": "Vendors describe agents that draft a threat model and a design security review without a person writing it first.",
   "Where a person approves": "Vendors describe the threat model as something the user reviews and approves before changes apply. Seezo describes no approval step; none found on 2026-11-19.",
   "What evidence it leaves": "Vendors describe audit logs, traceability or a record of decisions for the model.",
   "Vendors that publish an agent": "IriusRisk; Pixee; Rival Security; Seezo; Snyk; ThreatModeler",
   "Agents named (vendor: agent)": "IriusRisk: Jeff (AI threat modeling assistant); IriusRisk: MCP-connected AI agents; Pixee: Foresight (design-stage review); Rival Security: Threat model; Seezo: Seezo Agent and Seezo AI Plugin; Snyk: Evo Agentic Security Review; ThreatModeler: NexusAI; ThreatModeler: System Mapping Agent, Graph Agent, Reporting Agent",
   "Sources": "https://www.iriusrisk.com/ai-threat-modeling https://www.seezo.io/ https://www.threatmodeler.ai/ https://snyk.io/evo/agentic-appsec/ https://www.anthropic.com/engineering/building-effective-agents https://www.threatmodeler.ai/platform/nexusai https://genai.owasp.org/llmrisk/llm062025-excessive-agency/ https://artificialintelligenceact.eu/article/14/ https://www.seezo.io/seezo-ai-plugin https://github.com/mitre-atlas/atlas-data/blob/main/dist/ATLAS.yaml",
   "Read": "2026-11-19"
  },
  {
   "Job": "Access reviews",
   "What an agent reads": "Published agents read entitlement and identity data and the usage and risk context around each review item.",
   "What it does without a person": "Lumos describes an agent that certifies low-risk access itself and surfaces only the items needing a human call. Veza describes an agent that highlights risk and explains review items, with reviewers still deciding.",
   "Where a person approves": "Lumos describes customer-set policies and approval thresholds; Veza describes dual reviewer sign-off before certification completes.",
   "What evidence it leaves": "Lumos describes decisions stored as audit evidence. Veza's page: none found on 2026-11-19 for an agent audit trail.",
   "Vendors that publish an agent": "Lumos; Veza",
   "Agents named (vendor: agent)": "Lumos: Access Review Agent (with Albus); Veza: Access Review Agent (part of Veza Access Agents)",
   "Sources": "https://www.lumos.com/products/identity-agent-force https://veza.com/product/veza-access-agents/ https://genai.owasp.org/llmrisk/llm062025-excessive-agency/ https://veza.com/product/access-reviews/ https://artificialintelligenceact.eu/article/14/ https://www.lumos.com/products/access-reviews https://github.com/mitre-atlas/atlas-data/blob/main/dist/ATLAS.yaml",
   "Read": "2026-11-19"
  }
 ]
}