What is agentic AI in cybersecurity

Agentic AI in cybersecurity is a system in which a language model "dynamically" directs "its own processes and tool usage" (Anthropic's definition of an agent) to finish a security task, inside limits a team sets. ASD's ACSC and CISA used the term in guidance of 1 May 2026.

The definition, in the words of its sources

Anthropic separates two designs. Workflows are "systems where LLMs and tools are orchestrated through predefined code paths." Agents are "systems where LLMs dynamically direct their own processes and tool usage, maintaining control over how they accomplish tasks" (Building effective agents). The same post says agents suit problems "where it's difficult or impossible to predict the required number of steps" and warns of "higher costs, and the potential for compounding errors".

OWASP describes what makes such a system risky in security terms. Agency is "the ability to call functions or interface with other systems via extensions", and the choice of extension "may also be delegated to an LLM 'agent' to dynamically determine" (OWASP LLM06:2025).

LangChain names the code around the model the harness: "every piece of code, configuration, and execution logic that isn't the model itself", and adds "Agent = Model + Harness" (The Anatomy of an Agent Harness). Put together, an agent in security work is a model that chooses its next step, tools that read or change real systems, and a harness that sets what the tools may do. Permissions, approval and logging live in the harness; see the agent harness section.

Official guidance uses the term: ASD's ACSC, CISA and partners published "Careful Adoption of Agentic AI Services" on 1 May 2026, guidance for organizations adopting agentic AI systems (CISA); see official guidance.

One CVE, run as a workflow and as an agent

CISA added CVE-2026-46300, a Linux kernel flaw that lets a local low-privilege user reach root, to its Known Exploited Vulnerabilities catalog on 28 Oct 2026 with a due date of 31 Oct 2026. The task is to say which hosts are exposed. The fix had been public since 23 May 2026, when stable kernels 6.1.174, 6.6.141 and others shipped it.

The same finding handled two ways. Facts from the CVE-2026-46300 record, read 19 Nov 2026; the two columns are an illustration, not a vendor's product.
StepWorkflow (predefined path)Agent (model chooses the next step)
StartFixed script reads the inventory and runs uname -r on every Linux hostReads the KEV entry and the vendor advisories, then decides which checks the CVE needs
Version stringCompares the string with the fixed list: 6.1.174, 6.6.141, 6.12.91 and so onNotes that distribution kernels backport fixes without changing the upstream version, so it also searches the package changelog for the CVE
ExposureMarks every host in an affected range as exposedChecks whether the esp4 or esp6 modules are loaded and whether unprivileged user namespaces are allowed, because exposure needs both
Odd case: a 5.10 hostFinds no 5.10 entry in the fixed list and reports the host as affected with no fixed version to giveFinds the fix commit in the 5.10.257 stable changelog, so a 5.10 kernel at 5.10.257 or later has it, and that Debian bullseye ships it as 5.10.257-1; hands a 5.10 host below that or on another vendor's kernel to a person
Output and recordA list, identical on every run; the record is the script, its inputs and the output fileA written finding per host; may differ between runs; the record is the run log of each command and its output, the only way to see why two runs differ

A workflow author who knows the backport problem can add the changelog step. The agent's gain is handling the case nobody listed; its cost is that the set of possible actions is open, which is why the task spec lists each tool and the graded tool list says which calls wait for a person and what an agent should never do alone names the actions that always do.

When the label "agent" is wrong

Two questions test a product described as agentic:

  1. Can you list every action it may take before it runs? If yes, it is a workflow by Anthropic's definition. That is fine, and often better where the path is known; see agentic AI versus SOAR playbooks.
  2. Does it call tools that read or change systems, or only produce text for a person? A model that summarizes a finding is generative AI, not an agent; see agentic versus generative AI.

The agent framing is also the wrong choice for a task, whatever the product is called, in four cases. The path is known and repeats: Anthropic recommends "finding the simplest solution possible, and only increasing complexity when needed. This might mean not building agentic systems at all", and the CVE-2026-46300 version check above is such a task once the backport rule is written in. The output must be identical on every run, as in a compliance extract, which only the workflow column of the table gives. The end state cannot be checked by a rescan or a test, so nobody can tell a good run from a bad one. And the action is one the team cannot let a model choose, such as the seven in what an agent should never do alone: there the model may propose and a person acts.

Where to find vendors' agents

Vendors' agents are listed by job in the use-case matrix; to build one, start with how to use agentic AI in cybersecurity.

Sources

  1. Anthropic, Building effective agents, read 19 Nov 2026
  2. OWASP GenAI Security Project, LLM06:2025 Excessive Agency, read 19 Nov 2026
  3. LangChain, The Anatomy of an Agent Harness (March 2026), read 19 Nov 2026
  4. CISA, Known Exploited Vulnerabilities catalog entry for CVE-2026-46300, read 19 Nov 2026
  5. Red Hat, CVE-2026-46300, read 19 Nov 2026
  6. kernel.org, stable change log 6.1.174, read 19 Nov 2026
  7. kernel.org, stable change log 5.10.257 (commit 3599e6b3cc1a), read 19 Nov 2026
  8. Debian Security Tracker, CVE-2026-46300 (bullseye 5.10.257-1, DLA-4606-1), read 19 Nov 2026
  9. CISA, Careful Adoption of Agentic AI Services, read 19 Nov 2026

Last reviewed 19 Nov 2026