THE PERMISSION [LAYER]

AI agent incident

AI models helped researchers find PHP2Shell, two critical remote code execution flaws in PHP itself

Reported · 14 sources · CVE-2026-109618 · CVE-2026-109619

  • cve
  • ai-discovery

What happened

Two flaws in the PHP engine, CVE-2026-109618 and CVE-2026-109619, rated 9.2 on CVSS v4.0, let an unauthenticated web request run code on servers that use PHP to serve pages. They were found with the help of frontier AI models. Calif's Ryan Austin says an LLM agent reviewing PHP's source spotted the faulty code, and an LLM then turned the pattern into a reusable skill that found more variants; Wiz says it used Gemini 4 Argon and GPT-5.6 Sol to find the first bug on August 19 and to build and validate exploits; the CVE record credits OpenAI as finder. The CVE numbers leaked on October 20 and PHP moved its fix forward a day, releasing 8.5.12, 8.4.27, 8.3.36 and 8.2.35 on October 21; PHP 8.1 and older get no official release. Amazon logged one exploitation attempt on October 17, four days before disclosure, and security firms reported attempts after the patch. As of October 22 no successful compromise had been confirmed and neither flaw was in CISA's catalog of known exploited vulnerabilities.

Why it matters

AI-assisted source review found two critical bugs in one of the most widely deployed codebases on the web, and by Wiz's account the models also helped turn them into working exploits. AI shortened the embargo as well: Chainguard's chief executive told The Register his team rediscovered the bugs with an AI harness and a frontier model after hearing only that something was coming, and the PHP Foundation says Chainguard broke the embargo by publishing patched images before the release. Plan for fixes measured in hours, hunt from the earliest attempt rather than the disclosure date, and decide in advance what happens to hosts on unsupported versions, which CISA says to take offline until they can be patched.

Sources

  1. php.net PHP security advisory: Critical remote code execution vulnerabilities, update now
  2. GitHub RCE via OOM corruption (GHSA-w8hw-w9fx-j79w)
  3. cve.org CVE-2026-109618
  4. calif.io php2shell
  5. wiz.io PHP2Shell: AI uncovers critical RCE vulnerabilities affecting 70% of the Internet
  6. thephp.foundation Today's PHP Security Release, and How We're Strengthening PHP Security
  7. aws.amazon.com Amazon Threat Intelligence identifies PHP2Shell exploitation prior to public disclosure in MadPot
  8. CISA Critical Vulnerabilities in PHP Require Immediate Patching
  9. The Register PHP blames supply chain security biz Chainguard for putting entire web at risk
  10. The Hacker News PHP2Shell: Two Unpatched Critical PHP RCE Flaws (CVSS 9.2) Trigger Emergency Security Alert
  11. The Hacker News PHP2Shell: What Actually Protects You Before the 14:00 UTC PHP RCE Patch, and What Doesn't
  12. SecurityWeek PHP2Shell: Mass Exploitation Looms for Leaked Critical PHP Flaws
  13. CyberScoop PHP releases emergency fixes for 2 critical vulnerabilities
  14. Cybersecurity Dive Critical PHP vulnerabilities expose vast majority of websites to potential compromise

New incidents by email

Get incidents like this one in your inbox

New AI agent incidents are covered in the briefing, with what to check on the agents you already run. At least once a week, free.

You confirm by email. Unsubscribe in one click.

Background reading

AIVSS, explained An explainer on the problem behind this incident.

Cite or correct this record

“AI models helped researchers find PHP2Shell, two critical remote code execution flaws in PHP itself.” The Permission Layer AI Agent Incident Database, https://thepermissionlayer.com/incidents/php2shell-ai-found-php-rce-flaws/. Database updated October 22, 2026.

Every record traces to the dated sources above. If something here is wrong or missing, email [email protected] and it gets fixed. See this record in the full list.

The Permission Layer

Get the briefing by email

At least one email a week on AI agent identity, permissions, security and spend, written for the people who approve agent access. Five-minute read, free.

You confirm by email. Unsubscribe in one click.