Skip to content
aiqbenchAI & Quantum Intelligence
NewsInsightsBenchmarksSkillsAsk AILearnAbout
...Loading your session
NewsInsightsBenchmarksSkillsAsk AILearnAbout
Back to list
aiqbench takeAI Research

aiqbench analysis

Composing insight from the full article — this may take a moment.

3
Sources coveringarXiv, Cybersecurity News, Wiz

ChainAgent: Automated Chainable Vulnerability Discovery in PHP Web Applications

arXiv·November 20, 2026·3 min read

From arXiv

Full text

arXiv:2611.25412v1 Announce Type: cross Abstract: High-impact attacks on PHP web applications often chain limited-capability vulnerabilities with other flaws or intended behaviors. Discovering these chains requires identifying flaws and the dependencies enabling capability composition. Existing vulnerability discovery techniques analyze flaws in isolation, while attack planning assumes known components. This separation makes it difficult to discover previously unknown components whose security relevance becomes apparent only through their potential roles in an exploit chain.

We present ChainAgent, a goal-directed LLM-agent framework that jointly discovers exploit-chain components and their capability dependencies in source code. Guided by an empirical study of 386 real-world web exploit chains, ChainAgent represents vulnerabilities and functional gadgets--intended program behaviors that can be repurposed in attacks--through preconditions and capabilities over security-relevant objects. Instead of discovering vulnerabilities first and constructing attack paths afterward, ChainAgent uses an evolving exploit graph to guide source-code inspection.

It searches backward from unmet preconditions for capability producers and forward from discovered capabilities for functional gadgets that consume or amplify them. Object-centered chaining knowledge from our empirical study directs searches toward promising vulnerability classes, functional operations, and object accesses. We evaluate ChainAgent against Codex, a general-purpose coding agent, on 15 PHP applications across three shared LLM backends. ChainAgent achieves 42.02%--44.63% recall for goal-reaching components and recovers up to 4.4 times as many correct goal-reaching dependency edges as Codex. An additional evaluation of 30 real-world PHP applications identifies 20 vulnerabilities and 13 exploit chains, nine of which achieve remote code execution (RCE).

Abstract:High-impact attacks on PHP web applications often chain limited-capability vulnerabilities with other flaws or intended behaviors. Discovering these chains requires identifying flaws and the dependencies enabling capability composition. Existing vulnerability discovery techniques analyze flaws in isolation, while attack planning assumes known components. This separation makes it difficult to discover previously unknown components whose security relevance becomes apparent only through their potential roles in an exploit chain. We present ChainAgent, a goal-directed LLM-agent framework that jointly discovers exploit-chain components and their capability dependencies in source code.

Guided by an empirical study of 386 real-world web exploit chains, ChainAgent represents vulnerabilities and functional gadgets--intended program behaviors that can be repurposed in attacks--through preconditions and capabilities over security-relevant objects. Instead of discovering vulnerabilities first and constructing attack paths afterward, ChainAgent uses an evolving exploit graph to guide source-code inspection. It searches backward from unmet preconditions for capability producers and forward from discovered capabilities for functional gadgets that consume or amplify them.

Object-centered chaining knowledge from our empirical study directs searches toward promising vulnerability classes, functional operations, and object accesses. We evaluate ChainAgent against Codex, a general-purpose coding agent, on 15 PHP applications across three shared LLM backends. ChainAgent achieves 42.02%--44.63% recall for goal-reaching components and recovers up to 4.4 times as many correct goal-reaching dependency edges as Codex. An additional evaluation of 30 real-world PHP applications identifies 20 vulnerabilities and 13 exploit chains, nine of which achieve remote code execution (RCE).

Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)

arXiv:2611.25412 [cs.CR]

(or arXiv:2611.25412v1 [cs.CR] for this version)

https://doi.org/10.48550/arXiv.2611.25412 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Full text under the publisher's open licence · 336 words

Read at arXiv ↗Ask about this article

Other coverage of this story

  1. Nov 20arXiv · this article
  2. Nov 19Cybersecurity News · PHP Security Team Warns of Critical Vulnerabilities, Urges Users to Prepare for November 19 Updates
  3. Nov 19Wiz · phpAfterShell and Critical PHP RCE Vulnerabilities: Everything You Need To Know

Related coverage

Top 50 Best Penetration Testing Companies in 2026

Cybersecurity News · Jul 31, 2026

AI Safety

How information quality impacts LLMs' ability to patch complex, novel vulnerabilities

1Password · Aug 6, 2026

AI Safety

What 434 AI-Generated Vulnerabilities Reveal About Secure Software Development

Cybersecurity News · Jul 22, 2026

15 Best Patch Management Tools In 2027

Cybersecurity News · Nov 16, 2026

Other coverage of this story

  1. Nov 20arXiv · this article
  2. Nov 19Cybersecurity News · PHP Security Team Warns of Critical Vulnerabilities, Urges Users to Prepare for November 19 Updates
  3. Nov 19Wiz · phpAfterShell and Critical PHP RCE Vulnerabilities: Everything You Need To Know

Article info

Source

arXiv

Published

November 20, 2026

Read time

3 min

Category

AI Research
aiqbench
AI & Quantum Intelligence© aiqbench. All rights reserved.

Feeds:RSS·JSON Feed

LanguageEnglish·Românăbeta
NewsAI & TechQuantumInsights
ExploreBenchmarksLearn
CompanyAboutTrustLegal noticeTerms of ServicePrivacy PolicyCopyright noticesData erasureReport content

The aiqbench take, the insights, the daily digest and Ask answers are written by AI models from the sources shown, without editorial review before publication. They may contain errors — check the source. How the model is used →

  • News
  • Insights
  • Ask AI
  • Benchmarks
  • Account