AI agents for cloud security posture

As of 19 Nov 2026, seven vendors publish an agent for cloud misconfiguration findings, and they differ on one point: whether it changes anything. Prowler's Lighthouse AI cannot change the environment, while Wiz describes automatic remediation at high confidence.

An agent investigates cloud misconfiguration findings and proposes or applies a fix.

Who owns the parts:

Reads (What an agent reads)

4 of 7 vendors quoted on what the agent reads

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

4 of 7 vendors let customers build or change the agent

Tools and permissions

If you buy: Inside the supplier’s settings. 4 of 7 vendors listed for this job state on their pages that customers can build or change the agent; for the other 3, 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

4 of 7 vendors describe an approval step

Approval rules

If you buy: Where the product offers them. 4 of 7 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

4 of 7 vendors describe an audit trail

Logs

If you buy: What the product records. 4 of 7 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, from read-only to automatic

This job has the widest spread of autonomy among the six on this site. Prowler's Lighthouse AI explains findings and maps them to compliance controls, and states that it "has no tools to change your environment" (Prowler). At the other end, Wiz describes configuring the Green Agent to "automatically trigger remediation actions" when it reaches a high-confidence decision, such as blocking public S3 access or patching a vulnerable workload (Wiz agents post). Averlon's Infrastructure Risk PreCog Agent "evaluates proposed infrastructure changes before they are merged" (Averlon 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 jobInfrastructure Risk PreCog Agent
    What the vendor says it doesVendor says it evaluates proposed infrastructure changes in CI before …
    Full text

    Vendor says it evaluates proposed infrastructure changes in CI before they merge, determines whether a change would lead to exposure in the customer's environment, and delivers the fix to the developer at the same moment as the alert (platform page).

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

    None found on 19 Nov 2026. Checked the platform page, the home page and the remediation blog post; none describes customers building or editing their own agents. The blog says the remediation actions are used from the GitHub Marketplace and added to a workflow.

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

    None found on 19 Nov 2026 on the pages read for: a log of agent actions or an approval setting beyond the team's decision on the pull request.

  • Agent named for this jobProwler Lighthouse AI
    What the vendor says it doesVendor says it explains findings and maps them to compliance …
    Full text

    Vendor says it explains findings and maps them to compliance controls (vendor claim).

    Customer can build or change agentsYes
    Full text

    Yes. Customers choose the model it runs on (OpenAI, Amazon Bedrock or an OpenAI-compatible model). The Prowler MCP Server also connects a customer's own agents.

    Limits stated, or none foundRead only: it advises and does not fix
  • Agent named for this jobCloud posture
    What the vendor says it doesVendor claim: a built-in agent that sorts cloud misconfigurations by …
    Full text

    Vendor claim: a built-in agent that sorts cloud misconfigurations by risk (Rival home page). The page does not say that it changes anything.

    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 jobPosture agent (Sysdig Agentic AI)
    What the vendor says it doesVendor says agents handle heavy lifting once outcomes are defined (vendor claim)
    Customer can build or change agentsYes
    Full text

    Yes. The agent builds custom policies for the environment, and a separate Headless Cloud Security offering lets customers build workflows through their own AI agents.

    Limits stated, or none foundNone found on 19 Nov 2026 for stated limits of the Posture agent
  • Agent named for this jobTami
    What the vendor says it doesVendor claim: investigates read-only first and publishes what it declined …
    Full text

    Vendor claim: investigates read-only first and publishes what it declined to change, with evidence.

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

    None found on 19 Nov 2026. Checked the home and product pages; no customer-authored agent feature. The product page says it builds a memory of what the team approves.

    Limits stated, or none foundCloud misconfiguration findings only; none found on 2026-11-19: code or …
    Full text

    Cloud misconfiguration findings only; none found on 2026-11-19: code or dependency fixes on the pages read.

  • Agent named for this jobGreen (Upwind's own agent, with Blue and Red; not Wiz's Green Agent)
    What the vendor says it doesVendor says Green drives remediation of prioritized issues (vendor claim)
    Customer can build or change agentsNone found on 19 Nov 2026
    Full text

    None found on 19 Nov 2026. The agentic security page and homepage describe no way for customers to build or change agents.

    Limits stated, or none foundNone found on 19 Nov 2026 for approval, audit or customization of …
    Full text

    None found on 19 Nov 2026 for approval, audit or customization of the Green agent.

  • Agent named for this jobGreen Agent (cloud misconfiguration remediation)
    What the vendor says it doesWiz's claim: the Green Agent ties each Issue to code-to-cloud …
    Full text

    Wiz's claim: the Green Agent ties each Issue to code-to-cloud context and ownership to give environment-specific remediation steps.

    Customer can build or change agentsYes
    Full text

    Yes. Wiz Workflows let a team define when agents act and where a person must approve. Building a new agent from scratch is not described.

    Limits stated, or none foundWiz's Red Agent (offensive testing) and Blue Agent (threat investigation) …
    Full text

    Wiz's Red Agent (offensive testing) and Blue Agent (threat investigation) fall outside the six jobs; a Wiz agent for new-disclosure response, threat modeling or access reviews: none found on 19 Nov 2026 on the two blog pages checked.

Confidence or impact decides who acts

Wiz routes by confidence: it acts at a high-confidence decision and sends lower-confidence remediation from the Green Agent to a developer in Slack for approval. Its Green Agent gives each Issue a Remediate or Ignore decision with a confidence figure, and marks steps that could affect availability as Suggested or Optional (Wiz Green Agent). Wiz Workflows can add a human approval step before remediation or before a Jira ticket.

Sysdig routes by impact: routine analysis runs on its own and high-impact actions go to the team for approval first (Sysdig). A team adopting either should define high-impact in its own terms before the first run, for example any change to identity policy, network exposure or encryption.

Tamnoon's page says fixes run through the customer's own change process, unsafe fixes are declined in writing, and the agent investigates read-only first. A log of what the agent chose not to change shows whether it applies judgment or fixes everything (vendor claims). With Prowler there is nothing for an approval step to gate; the approval question moves to whoever runs the commands it suggests. For Rival's cloud posture agent its pages name no approval step (none found on 19 Nov 2026); the pull request review described for its fix agents belongs to those agents, so it is not counted. Averlon is counted under the same rule because its blog says the team can block or fix the change on the pull request before production.

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
AverlonIts blog says that with the PreCog finding on the pull request, "the team can block or fix the change before it ever reaches production" (vendor claim).None found on 19 Nov 2026
Prowler"Lighthouse AI has no tools to change your environment."None found on 19 Nov 2026
Rival SecurityNone found on 19 Nov 2026 for the cloud posture agent. The pull request review described for Rival's fix agents does not apply to it"Every agent action is traced, auditable and held to your policies, from the first prompt to the last change in production." (home page, all agents)
Sysdig"high-impact actions come to your team for approval first""Every action is recorded along with the reasoning behind it"
Tamnoon"Tamnoon proves each remediation safe and runs it through your own change process.""decision record retained, auditor-readable, attributable"
UpwindNone found on 19 Nov 2026None found on 19 Nov 2026
Wiz"Route lower-confidence remediation ... from the Green Agent to a developer in Slack for approval""Teams can follow this analysis directly in the Investigation tab, where each step in the Green Agent’s analysis is laid out."

The record to keep, and the reversal to obtain

  • The resource, account and region touched, and the configuration before and after.
  • The finding the change answered, and whether a rescan closed it.
  • For pre-merge checks of the Averlon kind: the proposed infrastructure change and the agent's decision.
  • The agent's stated reasoning. Sysdig says each action is recorded with its reasoning and Wiz lays out each step in an Investigation tab; neither page says the record can be exported to your own log store (none found on 19 Nov 2026).
  • The approver, or the rule that allowed the change to run unattended.
  • The way back: the prior configuration and the command or pipeline that restores it.

The posture pages for this job quote no rollback step, and Upwind's page names no approval, audit or customization for its Green agent, which is not Wiz's Green Agent (none found on 19 Nov 2026). Treat "how do I undo it" as a written answer to obtain before enabling automatic remediation; the checklist items on kill switch and rollback and verifying after each change set out the questions.

Worked example: one public bucket finding on 3 Nov 2026

The date is a real calendar date (a Tuesday); the bucket and the outcomes are illustrative. On 3 Nov 2026 a scanner raises a public-read finding on two storage buckets. Blocking public access is the very action Wiz names as its automatic example, so the finding is the same and the right answer differs.

  • Bucket A holds customer invoices and nothing links to it. A high-confidence block is safe. Under a Wiz-style rule it runs on its own; under Sysdig's impact rule it waits only if the team defined storage exposure as high impact. The record holds the public-access setting before (off) and after (on). Capture the before state with aws s3api get-public-access-block --bucket BUCKET-A, which returns NoSuchPublicAccessBlockConfiguration when none is set. The restore command for the block is aws s3api delete-public-access-block --bucket BUCKET-A when the before state was no configuration, or aws s3api put-public-access-block --bucket BUCKET-A --public-access-block-configuration BlockPublicAcls=false,IgnorePublicAcls=false,BlockPublicPolicy=false,RestrictPublicBuckets=false to put back the four settings you captured. Restoring reopens the invoices, so it needs the same approver as the block.
  • Bucket B serves the product images on the company website through a public URL. Blocking public access takes the site's images down. Before any block, test whether a bucket is serving traffic: read its server access logs for requests from outside the account over the last 30 days (aws s3api get-bucket-logging --bucket BUCKET-B shows whether they are on), and list the CloudFront distributions that name it as an origin (aws cloudfront list-distributions --query "DistributionList.Items[?Origins.Items[?contains(DomainName, 'BUCKET-B')]].Id"). Bucket A shows no outside requests and no distribution; bucket B shows both, and that result, not the agent's confidence figure, decides the routing. This is the kind of step Wiz says it marks Suggested or Optional because it could affect availability, and the case where the usual answer is wrong: the agent should route it to the bucket's owner, or decline in writing as Tamnoon describes, with the fix being a CDN in front of a private bucket.
  • With a read-only agent such as Prowler's, both buckets arrive as explanations mapped to compliance controls, and a person runs the change.
  • On 4 Nov 2026 the rescan must show bucket A closed. Check the account's own state, not the agent's report, and keep the restore step for bucket A in the record.
  • A documented case of the pre-merge kind, from Averlon's blog (customer unnamed, no date given): a Terraform change would have made two EC2 instances reachable from the internet. Both carried critical remote code execution vulnerabilities in Git and Binutils, and PreCog rated the change critical on the pull request so the team could block or fix it before production. Here the approval point is the pull request itself, and the record is the finding attached to it.

Risk: standing memory and context

MITRE ATLAS describes AI Agent Context Poisoning (AML.T0080): "Adversaries may attempt to manipulate the context used by an AI agent's large language model (LLM) to influence the responses it generates or actions it takes." (MITRE ATLAS). It bears on Tamnoon's memory of what the team approves and on any agent that learns from past approvals: a poisoned memory of "approved" could widen what runs unattended. Review that memory as you would a change to the approval policy.

Sources

  1. wiz.io/blog/introducing-wiz-green-agent, read 19 Nov 2026
  2. averlon.ai/blog/automating-remediation-application-infras..., read 19 Nov 2026
  3. averlon.ai/platform, read 19 Nov 2026
  4. averlon.ai, read 19 Nov 2026
  5. prowler.com/lighthouse-ai, read 19 Nov 2026
  6. prowler.com, read 19 Nov 2026
  7. rival.security, read 19 Nov 2026
  8. docs.rival.security, read 19 Nov 2026
  9. rival.security/use-cases, read 19 Nov 2026
  10. sysdig.com/products/agentic-ai, read 19 Nov 2026
  11. sysdig.com, read 19 Nov 2026
  12. tamnoon.io/product, read 19 Nov 2026
  13. tamnoon.io, read 19 Nov 2026
  14. upwind.io/agentic-security, read 19 Nov 2026
  15. upwind.io, read 19 Nov 2026
  16. upwind.io/ai-security-platform, read 19 Nov 2026
  17. wiz.io/blog/introducing-wiz-agents, read 19 Nov 2026
  18. github.com/mitre-atlas/atlas-data/blob/main/dist/ATLAS.yaml, read 19 Nov 2026

Last reviewed 19 Nov 2026