Cyber Security News

New AI Tool To Discover 0-Days At Large Scale With A Click Of A Button

Vulnhuntr, a static code analyzer using large language models (LLMs), discovered over a dozen zero-day vulnerabilities in popular open-source AI projects on Github (over 10,000 stars) within hours. 

These vulnerabilities include Local File Inclusion (LFI), Cross-Site Scripting (XSS), Server-Side Request Forgery (SSRF), Remote Code Execution (RCE), Insecure Direct Object Reference (IDOR), and Arbitrary File Overwrite (AFO). 

Vulnhuntr is a security tool that utilizes Large Language Models (LLMs) to discover remotely exploitable vulnerabilities in Python codebases, which overcomes limitations of context window size in LLMs by analyzing code in small chunks and intelligently requesting relevant parts. 

entire call chain

It then reconstructs the call chain from user input to server output to confirm vulnerabilities by employing various prompt engineering techniques to guide the LLM toward a comprehensive analysis. 

Join ANY.RUN's FREE webinar on How to Improve Threat Investigations on Oct 23 - Register Here 

While currently limited to Python and focusing on specific vulnerabilities, it offers a significant improvement over static code analyzers in identifying complex multi-step vulnerabilities with minimized false positives and negatives.

Researchers explored retrieving Augmented Generation (RAG) and fine-tuning large language models (LLMs) to identify vulnerability call chains in code. 

MyClass code

RAG proved inaccurate due to ambiguity in function names, while fine-tuning models yielded high false positives and struggled with multi-file vulnerabilities, while static parsing, particularly for dynamically typed languages like Python, presented challenges due to runtime modifications and limitations of static analysis tools. 

The solution involved providing the LLM with the exact line of code where a function is called, along with the function name, which allows for targeted file and function location within the project, improving call chain accuracy. 

The slight variation turns it from blind SSRF into nonblind SSRF.

It is a tool that utilizes Large Language Models (LLMs) to detect vulnerabilities in Python code by analyzing files handling remote user input and identifying potential weaknesses, as users can run it on entire repositories or specific files for better efficiency. 

Vulnhuntr assigns confidence scores (1–10) to findings, with higher scores indicating a greater likelihood of an actual vulnerability.

In the future, as LLMs become more powerful, static code parsing might become less important, but focusing on the call chain between user input and server output should still improve accuracy in vulnerability detection. 

Exploit of xss

Protext AI identified several critical vulnerabilities, where an RCE vulnerability allows attackers to execute arbitrary code due to a lack of input validation in a custom component functionality. 

SSRF vulnerabilities exist in multiple functions where user-controlled URLs are used without proper sanitization, potentially enabling internal resource access. 

An IDOR vulnerability in a PUT endpoint lets attackers modify messages they shouldn’t have access to, while LFI and AFO vulnerabilities arise from insufficient filename sanitization during file uploads. 

XSS vulnerabilities are present due to a lack of output encoding and user-controlled content handling, which pose a severe security risk and require immediate attention. 

How to Choose an ultimate Managed SIEM solution for Your Security Team -> Download Free Guide (PDF)

Aman Mishra

Recent Posts

Nearest Neighbor Attacks: Russian APT Hack The Target By Exploiting Nearby Wi-Fi Networks

Recent research has revealed that a Russian advanced persistent threat (APT) group, tracked as "GruesomeLarch"…

24 hours ago

240+ Domains Used By PhaaS Platform ONNX Seized by Microsoft

Microsoft's Digital Crimes Unit (DCU) has disrupted a significant phishing-as-a-service (PhaaS) operation run by Egypt-based…

2 days ago

Russian TAG-110 Hacked 60+ Users With HTML Loaded & Python Backdoor

The Russian threat group TAG-110, linked to BlueDelta (APT28), is actively targeting organizations in Central…

2 days ago

Earth Kasha Upgraded Their Arsenal With New Tactics To Attack Organizations

Earth Kasha, a threat actor linked to APT10, has expanded its targeting scope to India,…

2 days ago

Raspberry Robin Employs TOR Network For C2 Servers Communication

Raspberry Robin, a stealthy malware discovered in 2021, leverages advanced obfuscation techniques to evade detection…

2 days ago

145,000 ICS Systems, Thousands of HMIs Exposed to Cyber Attacks

Critical infrastructure, the lifeblood of modern society, is under increasing threat as a new report…

2 days ago