AWS CVEs 2024-2026: Is AI Finding the Bugs, or Writing Them? AWS published 184 security bulletins in 2026 through November 16, up from 32 in 2025 and 15 in 2024, according to an analysis of the AWS Security Bulletins page covering 231 bulletins and 298 unique CVEs. The analysis found AI developer tools (MCP servers, Kiro, Amazon Q, Amazon Bedrock AgentCore and Strands Agents) went from zero bulletins in 2024 to 50 in 2026, while database drivers rose from 1 to 26 and developer tooling such as the CDK, SAM and SDKs from 0 to 30. The author weighs whether AI agents are finding more bugs, AI-assisted coding is writing more of them, or AWS is simply disclosing more, noting researcher write-ups showed two to seven months from report to public disclosure. Writing AWS CVEs 2024-2026: Is AI Finding the Bugs, or Writing Them? On this page It started with a simple question late on a Monday night. How many CVEs has AWS published over the last three years? I figured it would be a quick count. A few dozen a year, maybe. Something I could eyeball over a cup of matcha Not really, matcha is disgusting… . It was not. 15 security bulletins in 2024. 32 in 2025. 184 in 2026, and the year is not even over. That is one hell of a hockey stick . And the question that follows is the one everyone in our industry is asking right now. Is this happening because AI is finding more bugs, or because AI is writing more of them? So I went digging. And yes, the irony is not lost on me: I used an AI agent to do a big chunk of the digging. More on that at the end What I looked at The source of truth here is the AWS Security Bulletins https://aws.amazon.com/security/security-bulletins/ page. I pulled every bulletin published from January 2024 up to bulletin 2026-184 November 16, 2026 . That came to 231 bulletins covering 298 unique CVEs . For each one I collected: 1. The bulletin ID, scope, content type and publication date. 2. Every CVE it lists some only mention them in the body, not the title, thanks for that btw . 3. Who AWS credits for reporting it. 4. The official CVE record from CVE List V5 https://github.com/CVEProject/cvelistV5 , with its reserved and published dates. 5. Where it existed, the researcher’s own write-up with their disclosure timeline. One thing I learned the hard way. I assumed the date a CVE ID is reserved would tell me roughly when a bug was reported. Nope. AWS reserves most of its own CVE IDs within a day of publishing them 193 of the 257 it issued itself, median gap of one day . So that date tells you nothing about when the bug was actually found. The real timelines only come from the researchers themselves. And they are eye-opening. Miggo https://www.miggo.io/post/albeast-security-advisory-alb-vulnerability reported ALBeast on April 6, 2024. The CVE https://aws.amazon.com/security/security-bulletins/AWS-2024-012/ showed up on October 21. Rhino Security Labs https://rhinosecuritylabs.com/research/unauthenticated-username-enumeration-in-aws waited four months for their IAM username enumeration CVE. Wiz reported CodeBreach https://www.wiz.io/blog/wiz-research-codebreach-vulnerability-aws-codebuild on August 25, 2025, AWS fixed it two days later, and the world heard about it in January 2026. Across the researcher write-ups I found, it was two to seven months from report to public. How many CVEs has AWS published since 2024? Two things jump out. First, 2024 and 2025 were both small years, even if 2025 doubled. Then nothing much happened in early 2026 either. January and February had four bulletins between them. The curve only breaks in the second quarter, and it has not slowed down since. October 2026 alone had 41 bulletins. That is more than the whole of 2025. Second, it is not one product dragging the numbers up. Yes, the new AI developer tools MCP servers, Kiro, Amazon Q, the Amazon Bedrock AgentCore and Strands Agents frameworks went from zero bulletins in 2024 to 50 in 2026. But plain old database drivers went 1, 2, 26. Developer tooling like the CDK, SAM and the SDKs went 0, 6, 30. Someone is going through the entire catalog. Is AI finding the AWS bugs, or writing them? There are three explanations I keep hearing, and all of them sound convincing. 1. AI is finding the bugs. Security researchers now have agents that can read a whole codebase and poke at it 24 hours a day. More eyes, tireless eyes, more CVEs. 2. AI is writing the bugs. Teams are shipping code with Kiro, Amazon Q, Claude Code and friends at a pace nobody could keep up with two years ago. Faster code, more holes. 3. AWS is simply telling us more. The boring answer. And sometimes the boring answer is the right one. There is evidence for all three in the bulletins themselves. On the finding side, outside reporters were credited on 13 bulletins in 2025 and 102 in 2026. And for the first time, the credits name AI directly: Anthropic on three bulletins Firecracker https://aws.amazon.com/security/security-bulletins/2026-015-aws/ , FreeRTOS-Kernel https://aws.amazon.com/security/security-bulletins/2026-138-aws/ and FreeRTOS-Kernel again https://aws.amazon.com/security/security-bulletins/2026-158-aws/ , with Claude itself named on that last one , the AISLE research team https://aws.amazon.com/security/security-bulletins/2026-005-AWS/ , plus AI security startups like pwn.ai https://aws.amazon.com/security/security-bulletins/2026-137-aws/ and Corsen AI https://aws.amazon.com/security/security-bulletins/2026-104-aws/ . All of them in 2026. Outside AWS’s own pages, the CVE record for the Node.js Brotli bug https://www.cve.org/CVERecord?id=CVE-2026-111497 credits OpenAI Codex Security as the finder. On the disclosure side, AWS assigned 45% of the CVEs in its own bulletins in 2024, 79% in 2025 and 92% in 2026. AWS now issues CVEs for things like sample code and a setup guide. That shift started a year before the surge, so it explains part of the curve, but not the 2026 jump on its own. And on the writing side? The bulletins can’t tell you. A bulletin says what broke, not who or what wrote it. So the only way to answer that one is to go to the code. Tracing CVEs back to the commit with git blame Most of the affected code is open source, which means the evidence is sitting right there in git. So the plan was simple on paper : 1. Find the commit that fixed each CVE 2. Look at the lines that fix changed, and run git blame on them to find the commit that introduced the vulnerable code 3. Check both commits for AI fingerprints Step 2 looks something like this: the lines the fix touched, blamed in the commit just before the fix git blame -w --line-porcelain -L 120,148