AI agents for response to a new disclosure

As of 19 Nov 2026, 10 vendors publish an agent that matches a newly disclosed vulnerability to a customer's own assets and proposes next steps. The page shows where a person approves, what record to keep, and a worked example that follows CVE-2026-111497 from the 14 Oct 2026 pre-alert to the 10 Nov CISA due date.

When a new CVE or advisory is published, an agent finds which of the customer's assets are affected and proposes what to do now.

Who owns the parts:

Reads (What an agent reads)

4 of 10 vendors quoted on what the agent reads

Does alone (What it does without a person)Supplier’s settingsYours

4 of 10 vendors let customers build or change the agent

Tools and permissions

If you buy: Inside the supplier’s settings. 4 of 10 vendors listed for this job state on their pages that customers can build or change the agent; for the other 6, none found on 19 Nov 2026.

Source

NIST AI RMF 1.0: “MAP 4: Risks and benefits are mapped for all components of the AI system including third-party software and data.”

If you build: You grant each tool and each credential.

Source

OWASP LLM06:2025 Excessive Agency: “Limit the permissions that LLM extensions are granted to other systems to the minimum necessary in order to limit the scope of undesirable actions.”

A person approves (Where a person approves)Where offeredYours

6 of 10 vendors describe an approval step

Approval rules

If you buy: Where the product offers them. 6 of 10 vendors listed for this job describe an approval step on the pages read 19 Nov 2026.

Source

OWASP LLM06:2025 Excessive Agency: “Utilise human-in-the-loop control to require a human to approve high-impact actions before they are taken.”

If you build: You write which actions wait for a person.

Source

OWASP LLM06:2025 Excessive Agency: “Utilise human-in-the-loop control to require a human to approve high-impact actions before they are taken.”

Evidence (What evidence it leaves)Product recordsYours

6 of 10 vendors describe an audit trail

Logs

If you buy: What the product records. 6 of 10 vendors listed for this job describe an audit trail on the pages read 19 Nov 2026.

Source

MITRE ATLAS mitigations: “When deploying AI agents, implement logging of the intermediate steps of agentic actions and decisions, data access and tool use, installation commands, and identity of the agent.”

If you build: You log every step where the agent cannot edit it.

Source

MITRE ATLAS mitigations: “When deploying AI agents, implement logging of the intermediate steps of agentic actions and decisions, data access and tool use, installation commands, and identity of the agent.”

Model choice

If you buy: The supplier picks and updates the model.

Source

NCSC, Guidelines for secure AI system development: “You support users to evaluate and respond to model changes (for example by providing preview access and versioned APIs).”

If you build: You pick the model and can swap it.

Source

Anthropic, Scaling Managed Agents: “This allows the implementation of each to be swapped without disturbing the others.”

The tables below carry the quotes. All read 19 Nov 2026; counts from the vendors directory.

What the agents do with a new advisory

The input is a new advisory plus the customer's own inventory. Astelia's Hunter agent checks newly disclosed and zero-day vulnerabilities against an SBOM and software list "to find what's reachable, even before scanners detect them" (Astelia). Seemplicity says its SCA Analyst powers SBOM-driven zero-day response before scanner signatures exist (Seemplicity). Cogent promises vulnerable software identified "within minutes of a new disclosure, before scanners can" (Cogent). These are vendor statements of speed with no method published on the pages read. The disclosures of the last two months and their CISA due dates are on dates to know.

Zafran's 88-second figure sits on a home page demonstration built around an OpenSSL pre-announcement of 25 October 2022, so it shows a flow rather than a measured result on a 2026 disclosure (Zafran). Onit's Zero-Day Agent gives each asset one of three outcomes, "exploitable in your environment, conditions not met, or could not verify", checks read-only through the customer's EDR and "does not run live exploits against production" (Onit). Its post is dated 23 Oct 2026 and says the full launch was the following week. Rival's write-up of PHP2Shell reports that for one unnamed customer a triaging agent found 60 repositories containing PHP, 29 of them potentially vulnerable, before scanners could detect the CVEs (vendor-reported, Rival blog).

Vendors with a published agent for this job, alphabetical, the same fields for each vendor, read 19 Nov 2026. Claims are the vendor's own. Dot: stated; ring: none found.

  • Agent named for this jobThe Hunter (Zero-Day Detection)
    What the vendor says it doesVendor claim: workflows are built from plain-language specs with fine-grained …
    Full text

    Vendor claim: workflows are built from plain-language specs with fine-grained tool scopes and human checkpoints, and run over 100+ integrations.

    Customer can build or change agentsYes
    Full text

    Yes. The launch post says customers describe a workflow in plain language to a planner agent, can create agents from scratch, or adjust templates from a marketplace.

    Limits stated, or none foundNone found on 19 Nov 2026 for code pull requests on the …
    Full text

    None found on 19 Nov 2026 for code pull requests on the pages read: fixes described are patches through patch tools, firewall and IPS rules, and tickets.

  • Agent named for this jobCogent AI agents (new disclosure)
    What the vendor says it doesVendor claim: autonomy is staged, starting with recommendations plus approval …
    Full text

    Vendor claim: autonomy is staged, starting with recommendations plus approval and widening as results hold up, with read-only access by default.

    Customer can build or change agentsNone found on 19 Nov 2026
    Full text

    None found on 19 Nov 2026. Checked the home page, AI engine, autonomy levels, Cyber Defense Factory and integrations pages. Customers configure approval gates, thresholds and policy limits but no page describes building custom agents.

    Limits stated, or none foundNone found on 19 Nov 2026 on the pages read for: code …
    Full text

    None found on 19 Nov 2026 on the pages read for: code pull request generation or customer-built agents; the autonomy-levels page shows operations such as patching and IAM token revocation as approval-gated examples.

  • Agent named for this jobMalware Responder (AURI Agent)
    What the vendor says it doesVendor claim: correlates live supply-chain malware intelligence against the customer's …
    Full text

    Vendor claim: correlates live supply-chain malware intelligence against the customer's inventory and returns affected projects, indicators of compromise and containment guidance. It answers a disclosed malicious package rather than a CVE.

    Customer can build or change agentsYes
    Full text

    Yes. Agents are published as open markdown files that can be read and forked; the Agents Hub itself does not yet add custom agents, but points to an open source route.

    Limits stated, or none foundYou can view the agents in the Agents Hub but …
    Full text

    You can view the agents in the Agents Hub but cannot yet add a custom agent inside Endor Labs.

  • Agent named for this jobMaze Cloud agents
    What the vendor says it doesVendor claim: when a new zero-day drops, agents sweep every …
    Full text

    Vendor claim: when a new zero-day drops, agents sweep every instance across the environment in hours, before scanners have a signature (Maze cloud page).

    Customer can build or change agentsNone found on 19 Nov 2026
    Full text

    None found on 19 Nov 2026. Checked the home, cloud, code and remediation pages; none describes customer-built agents.

    Limits stated, or none foundNone found on 19 Nov 2026 on the pages read for: customer-built …
    Full text

    None found on 19 Nov 2026 on the pages read for: customer-built agents or an action log; where no fix exists, agents recommend a mitigation instead (vendor statement).

  • Agent named for this jobZero-Day Agent
    What the vendor says it doesVendor claim: approved decisions become standing rules so matching exposures …
    Full text

    Vendor claim: approved decisions become standing rules so matching exposures are handled without repeat review, with each action logged and reversible.

    Customer can build or change agentsNone found on 19 Nov 2026
    Full text

    None found on 19 Nov 2026. Checked the platform page, home page and both blog posts. A team can adjust one agent's behavior and calibrate behavior through decisions, but no page describes building new agents.

    Limits stated, or none foundNone found on 19 Nov 2026 on the pages read for: customer-built …
    Full text

    None found on 19 Nov 2026 on the pages read for: customer-built agents or an opened pull request; the Zero-Day post (dated 23 Oct 2026) said its full launch was the following week.

  • Agent named for this jobAgent Insta; Agent Nyra
    What the vendor says it doesVendor claim: Agent Insta correlates new advisories with live inventory …
    Full text

    Vendor claim: Agent Insta correlates new advisories with live inventory and telemetry; Agent Nyra maps weaponized CVEs to the customer's impacted assets and reorders the backlog.

    Customer can build or change agentsNone found on 19 Nov 2026
    Full text

    None found on 19 Nov 2026. No customer-authored agent feature appeared on the three Qualys pages read. Customers do set the policies and maintenance windows that Qualys's patching agent works within.

    Limits stated, or none foundAgent Grant (identity attack surface) is labeled coming soon; none …
    Full text

    Agent Grant (identity attack surface) is labeled coming soon; none found on 2026-11-19: customer-built agents on the pages read.

  • Agent named for this job0-day response
    What the vendor says it doesVendor claim: one harness with built-in, vendor-built and customer-built agents, …
    Full text

    Vendor claim: one harness with built-in, vendor-built and customer-built agents, and a published write-up of agents triaging PHP2Shell exposure across customer repositories before scanners could detect the CVEs.

    Customer can build or change agentsYes
    Full text

    Yes. The home page offers three routes: use ready-made agents and extend them, have Rival engineers build tailored agents, or build your own.

    Limits stated, or none foundNone found on 19 Nov 2026 for: public documentation, pricing, or named …
    Full text

    None found on 19 Nov 2026 for: public documentation, pricing, or named customers on the pages read.

  • Agent named for this jobSCA Analyst
    What the vendor says it doesVendor claim: each analyst returns a decision with its evidence, …
    Full text

    Vendor claim: each analyst returns a decision with its evidence, fix options and a likely owner.

    Customer can build or change agentsNone found on 19 Nov 2026
    Full text

    None found on 19 Nov 2026. Neither the home page nor the AI Analysts article nor the agentic workforce page mentions customer-built agents.

    Limits stated, or none foundNone found on 2026-11-19: approval gates, customer-built agents, or a …
    Full text

    None found on 2026-11-19: approval gates, customer-built agents, or a date on the home page for the analyst list.

  • Agent named for this jobScriptAI
    What the vendor says it doesVendor claim: AI scripts are held as drafts until a …
    Full text

    Vendor claim: AI scripts are held as drafts until a human reviews and publishes them.

    Customer can build or change agentsNone found on 19 Nov 2026 for building or changing agents
    Full text

    None found on 19 Nov 2026 for building or changing agents. Any team member can describe a scripting need in plain language and ScriptAI generates a script for the private library; that is script authoring.

    Limits stated, or none foundVendor states a 95% false-positive cut with no method on …
    Full text

    Vendor states a 95% false-positive cut with no method on the page; none found on 19 Nov 2026: a log of ScriptAI's own generation decisions (the page says script executions inherit operator logging and timestamped results).

  • Agent named for this jobZero Day Agent
    What the vendor says it doesVendor claim: routes remediation work to owners through existing ticketing …
    Full text

    Vendor claim: routes remediation work to owners through existing ticketing and consolidates overlapping tasks.

    Customer can build or change agentsYes
    Full text

    Yes. A customer testimonial on the home page says users can create their own agent, and the product mock shows a prompt to create a scheduled report agent. Scope not documented on the pages read.

    Limits stated, or none foundNone found on 2026-11-19: pull requests as a remediation output …
    Full text

    None found on 2026-11-19: pull requests as a remediation output on the home and platform pages; work is routed as tickets.

Approval gates under a clock

A disclosure agent works against a deadline, which is when a team is most tempted to let it act. Vicarius holds ScriptAI scripts as drafts until a person publishes them (Vicarius). Zafran says approval workflows apply at every step of its remediation, and Astelia's example workflow leaves a drafted ticket and a proposed firewall rule in an approval queue until a person clicks (Astelia). Qualys keeps changes under existing process through condition-based patch blocking and a ServiceNow change integration (Qualys). Onit's post says a person approves the decision before disruptive action. Run each gate once under a drill clock, because the useful test is whether it still holds when the team is in a hurry.

Approval and evidence wording from each vendor's own pages, read 19 Nov 2026. These are descriptions, not test results.
VendorApproval point, in the vendor's wordsEvidence kept, in the vendor's words
Astelia"The drafted ticket and the proposed firewall rule wait in the approval queue for a human click""every step lands in the execution log, and every decision in the audit log."
Cogent Security"Decide where agents act independently and where they pause for sign-off. Configure by action type, severity, or asset sensitivity.""every agent action is logged with its reasoning."
Endor LabsNone found on 19 Nov 2026 for Malware Responder. The workflows page says agents are "Read-only by default with centralized visibility and approval gates", and that only SCA Remediation and AI SAST Remediation change state, each behind a separate approval gate.None found on 19 Nov 2026. The Agents Hub view is described as usage metering, not a compliance audit log.
MazeNone found on 19 Nov 2026 for the zero-day sweep itself. Maze's remediation page, which covers the fixes its agents deliver, says "Your team stays in control of what gets merged."None found on 19 Nov 2026 for an agent action log. The pages say each recommendation carries its evidence and reasoning.
Onit Security"Every agent action passes an approval gate, writes to an audit trail, and is reversible in one step, across both remediations and mitigations.""Every conclusion traces back to the agent that produced it and the evidence it used."
Qualys"Condition-based patch blocking and the ServiceNow change integration keep every change under existing approval processes."None found on 19 Nov 2026 for Agent Insta or Agent Nyra. The audit trail Qualys describes belongs to Agent Val, a triage agent; see the triage page.
Rival SecurityNone found on 19 Nov 2026 for the 0-day response agent. The pull request review described on Rival's home page ("so your team reviews instead of digging") belongs to its fix agents; see the code and dependency fixes page."Every agent action is traced, auditable and held to your policies, from the first prompt to the last change in production."
SeemplicityNone found on 19 Nov 2026. The pages read say each analyst returns a decision, evidence, fix options and an owner, and describe no approval gate."an auditable trail"
Vicarius"No script generated by ScriptAI can reach a live asset without a human publishing it first."None found on 19 Nov 2026 for a log of ScriptAI's generation decisions. The page says "Every script execution inherits vRx's full audit infrastructure, including operator logging, asset-level output, and timestamped results".
Zafran"Keep humans in the loop with full command auditability and approval workflows at every step""full command auditability"

A halt is not enough for a disclosure agent, because a firewall rule or script it proposed may already be live. Onit says actions are reversible in one step (vendor claim) and Qualys describes automatic rollback to a known-good state. Ask for the reversal to be shown on a test host before the first real disclosure (kill switch and rollback). Boundaries on what an agent may do alone are in the guide to what an agent should never do alone.

The record to keep for each disclosure

Agent disclosure record

  • Advisory ID, and the time the agent first read it
  • Inventory snapshot used (SBOM or asset data), and its date
  • Per asset: affected, not affected, or could not verify, with the evidence
  • Method used to verify (for example a read-only check through EDR)
  • Proposed stopgap, and who must approve it
  • Time of approval, approver, and time the stopgap went live
  • Time and method of the rollback, if any

Download the template: .docx PDF CC BY 4.0

Onit's description is a useful benchmark: every conclusion traces back to the agent that produced it and the evidence it used (vendor statement, Onit AI agents post). Astelia, Seemplicity and Zafran each describe execution logs, audit trails or command auditability, and none of their pages shows the log itself.

Worked example: CVE-2026-111497 (Node2Shell), 14 Oct to 10 Nov 2026

CVE-2026-111497 is an out-of-bounds write in Google's Brotli decoder, bundled in Node.js, CVSS 3.1 score 9.8, CWE-787. Its timeline gives the agent's clock (NVD, the Node.js advisory, ELLIO and the CISA KEV entry, read 19 Nov 2026).

Dates from the sources named in the text, read 19 Nov 2026. Days are counted from 21 Oct 2026.
DateEventDays from the 21 Oct release
14 Oct 2026Node.js pre-alert of the 21 Oct release, naming the flaw as high severity7 days before
21 Oct 2026Node.js 22.23.4, 24.22.1 and 26.12.1 and Brotli 1.0.10, 1.1.1 and 1.2.1 released; advisory published0
22 Oct 2026NVD record and GitHub advisory published; public proof of concept appears1
26 Oct 2026First reported exploitation in the wild (ELLIO sensors)5
27 Oct 2026CISA adds it to KEV, due date 10 Nov 2026 (14 days after the listing)6 (the due date, 10 Nov, is 20)

The five assets belong to a constructed organisation, not a real one; the versions and checks come from the CVE record. An agent given the advisory on 21 Oct and the inventory has 5 days before exploitation was reported.

Inventory of a constructed organisation. Version facts: CVE-2026-111497 record, Node.js advisory 21 Oct 2026, ELLIO.
AssetWhat the agent findsOutcomeWho approves what
api-gateway, image pinned to node:24.22.024.22.0 is below 24.22.1, and a pinned tag stays vulnerable until the pin movesAffectedRebuild with node:24.22.1 in the normal change window; an emergency window needs a named approver
billing-worker, Node.js 22.23.4At or above the fixed 22.23.4. The check must be node --version: ELLIO reports that Node.js cherry-picked the fix without bumping the bundled version string, so process.versions.brotli reads 1.2.0 on both patched and vulnerable buildsNot affectedNone; the evidence is the version output
legacy-reports, Node.js 20.xEnd-of-life line, always affected, no fix issuedAffected, no patchA person decides on a move to a supported line and on the stopgap
ml-service, PyPI Brotli 1.2.0A separate copy of Brotli below the fixed 1.2.1; a Node.js upgrade does not touch itAffectedUpgrade Brotli to 1.2.1 through the pull request path
Vendor appliance embedding BrotliNo version data the agent can readCould not verifyA person asks the supplier; counting it as safe is the common failure

The exposure also depends on whether untrusted data reaches the decoder: inbound request bodies sent with Content-Encoding br on frameworks that inflate them, outbound responses fetched from URLs an attacker can influence, and direct calls. An agent that reports a path should show which of the three it checked.

The stopgap in the record is to reject inbound requests with Content-Encoding br at the proxy or load balancer. Its cost is an error for clients that send Brotli-compressed bodies, and it does not cover Brotli responses the application fetches from other servers. It changes live traffic, so it is the item a person approves, with the rollback time written next to it. Test the rule on a staging proxy before it goes live: send a request with the header (curl -i -X POST -H 'Content-Encoding: br' --data 'test' followed by the staging URL) and expect the rejection status you configured, for example 415; send the same request without the header and expect the normal response; send one with Content-Encoding: gzip and expect it to pass. Search the last 30 days of request logs for Content-Encoding br first, because any client that sends it will start to fail, and write the proxy change that removes the rule next to the approval. The Node.js advisory lists no workaround, so the stopgap comes from the researchers at Aikido, who say they used it on internal services that could not be upgraded right away, and ELLIO. By 10 Nov 2026 the five assets should read affected assets fixed or on an approved exception, and the could-not-verify count should be zero or owned.

Risk: poisoned advisory and feed content

The agent's inputs are text from advisories, blogs and feeds. MITRE ATLAS describes RAG Poisoning (AML.T0070): "Adversaries may inject malicious content into data indexed by a retrieval augmented generation (RAG) system to contaminate a future thread through RAG-based search results." (MITRE ATLAS). Take advisory facts such as fixed versions from the vendor's own advisory, and have the record cite it, so a reviewer can compare the agent's claim to the source.

Sources

  1. astelia.io/use-cases/deploy-astelia-agents, read 19 Nov 2026
  2. astelia.io/post/closing-the-exposure-loop, read 19 Nov 2026
  3. cogent.com, read 19 Nov 2026
  4. cogent.com/ai/cogent-ai-engine, read 19 Nov 2026
  5. cogent.com/ai/autonomy-levels, read 19 Nov 2026
  6. cogent.com/platform/cyber-defense-factory, read 19 Nov 2026
  7. cogent.com/platform/integrations, read 19 Nov 2026
  8. endorlabs.com/platform/agentic-workflows, read 19 Nov 2026
  9. endorlabs.com/solutions/agentic-remediation, read 19 Nov 2026
  10. docs.endorlabs.com/secure-ai-coding/agents-hub, read 19 Nov 2026
  11. mazehq.com/platform/cloud, read 19 Nov 2026
  12. mazehq.com, read 19 Nov 2026
  13. mazehq.com/platform/code, read 19 Nov 2026
  14. mazehq.com/solutions/remediation, read 19 Nov 2026
  15. onit.security/blog/zero-day-response, read 19 Nov 2026
  16. onit.security/blog/ai-agents-vulnerability-management, read 19 Nov 2026
  17. onit.security/platform, read 19 Nov 2026
  18. onit.security, read 19 Nov 2026
  19. qualys.com/apps/agentic-ai, read 19 Nov 2026
  20. qualys.com/apps/trurisk-eliminate, read 19 Nov 2026
  21. qualys.com/apps/enterprise-trurisk-management, read 19 Nov 2026
  22. rival.security, read 19 Nov 2026
  23. docs.rival.security, read 19 Nov 2026
  24. rival.security/use-cases, read 19 Nov 2026
  25. rival.security/blog/php2shell-black-october-2026, read 19 Nov 2026
  26. seemplicity.ai/news/ai-analysts-autonomous-vulnerability-..., read 19 Nov 2026
  27. seemplicity.ai, read 19 Nov 2026
  28. seemplicity.ai/platform/agentic-workforce, read 19 Nov 2026
  29. vicarius.io/features/scriptai, read 19 Nov 2026
  30. vicarius.io/features/vrx-analysis, read 19 Nov 2026
  31. zafran.io, read 19 Nov 2026
  32. zafran.io/platform, read 19 Nov 2026
  33. MITRE ATLAS data, ATLAS.yaml (techniques and mitigations), read 19 Nov 2026
  34. Node.js, October 2026 security releases, read 19 Nov 2026
  35. CISA KEV entry for CVE-2026-111497, read 19 Nov 2026
  36. ELLIO, Node2Shell research, read 19 Nov 2026
  37. NVD record for CVE-2026-111497, read 19 Nov 2026
  38. Aikido, Node2Shell: Node.js Brotli vulnerability (CVE-2026-111497) and the fix, read 19 Nov 2026

Last reviewed 19 Nov 2026