• Home
  • Cyber Crime
  • Cyber warfare
  • APT
  • Data Breach
  • Deep Web
  • Digital ID
  • Hacking
  • Hacktivism
  • Intelligence
  • Internet of Things
  • Laws and regulations
  • Malware
  • Mobile
  • Reports
  • Security
  • Social Networks
  • Terrorism
  • ICS-SCADA
  • POLICIES
  • Contact me
MUST READ

Critical Sudo bugs expose major Linux distros to local Root exploits

 | 

Google fined $314M for misusing idle Android users' data

 | 

A flaw in Catwatchful spyware exposed logins of +62,000 users

 | 

China-linked group Houken hit French organizations using zero-days

 | 

Cybercriminals Target Brazil: 248,725 Exposed in CIEE One Data Breach

 | 

Europol shuts down Archetyp Market, longest-running dark web drug marketplace

 | 

Kelly Benefits data breach has impacted 550,000 people, and the situation continues to worsen as the investigation progresses

 | 

Cisco removed the backdoor account from its Unified Communications Manager

 | 

U.S. Sanctions Russia's Aeza Group for aiding crooks with bulletproof hosting

 | 

Qantas confirms customer data breach amid Scattered Spider attacks

 | 

CVE-2025-6554 is the fourth Chrome zero-day patched by Google in 2025

 | 

U.S. CISA adds TeleMessage TM SGNL flaws to its Known Exploited Vulnerabilities catalog

 | 

A sophisticated cyberattack hit the International Criminal Court

 | 

Esse Health data breach impacted 263,000 individuals

 | 

Europol dismantles €460M crypto scam targeting 5,000 victims worldwide

 | 

CISA and U.S. Agencies warn of ongoing Iranian cyber threats to critical infrastructure

 | 

U.S. CISA adds Citrix NetScaler flaw to its Known Exploited Vulnerabilities catalog

 | 

Canada bans Hikvision over national security concerns

 | 

Denmark moves to protect personal identity from deepfakes with new copyright law

 | 

Ahold Delhaize data breach affected over 2.2 Million individuals

 | 
  • Home
  • Cyber Crime
  • Cyber warfare
  • APT
  • Data Breach
  • Deep Web
  • Digital ID
  • Hacking
  • Hacktivism
  • Intelligence
  • Internet of Things
  • Laws and regulations
  • Malware
  • Mobile
  • Reports
  • Security
  • Social Networks
  • Terrorism
  • ICS-SCADA
  • POLICIES
  • Contact me
  • Home
  • Breaking News
  • Security
  • OWASP Top 10 for LLM (Large Language Model) applications is out!

OWASP Top 10 for LLM (Large Language Model) applications is out!

Pierluigi Paganini August 03, 2023

The OWASP Top 10 for LLM (Large Language Model) Applications version 1.0 is out, it focuses on the potential security risks when using LLMs.

OWASP released the OWASP Top 10 for LLM (Large Language Model) Applications project, which provides a list of the top 10 most critical vulnerabilities impacting LLM applications.

The project aims to educate developers, designers, architects, managers, and organizations about the security issues when deploying Large Language Models (LLMs).

The organization is committed to raising awareness of the vulnerabilities and providing recommendations for hardening LLM applications.

“The OWASP Top 10 for LLM Applications Working Group is dedicated to developing a Top 10 list of vulnerabilities specifically applicable to applications leveraging Large Language Models (LLMs).” reads the announcement of the Working Group. “This initiative aligns with the broader goals of the OWASP Foundation to foster a more secure cyberspace and is in line with the overarching intention behind all OWASP Top 10 lists.”

OWASP Top 10 for LLM

The organization states that the primary audience for its Top 10 is developers and security experts who design and implement LLM applications. However the project could be interest to other stakeholders in the LLM ecosystem, including scholars, legal professionals, compliance officers, and end users.

“The goal of this Working Group is to provide a foundation for developers to create applications that include LLMs, ensuring these can be used securely and safely by a wide range of entities, from individuals and companies to governments and other organizations.” continues the announcement.

The Top Ten is the result of the work of nearly 500 security specialists, AI researchers, developers, industry leaders, and academics. Over 130 of these experts actively contributed to this guide.

Clearly the project is a work in progress, LLM technology continues to evolve, and the research on security risk will need to keep pace.

Below is the Owasp Top 10 for LLM version 1.0

LLM01: Prompt Injection

This manipulates a large language model (LLM) through crafty inputs, causing unintended actions by the LLM. Direct injections overwrite system prompts, while indirect ones manipulate inputs from external sources.

LLM02: Insecure Output Handling

This vulnerability occurs when an LLM output is accepted without scrutiny, exposing backend systems. Misuse may lead to severe consequences like XSS, CSRF, SSRF, privilege escalation, or remote code execution.

LLM03: Training Data Poisoning

This occurs when LLM training data is tampered, introducing vulnerabilities or biases that compromise security, effectiveness, or ethical behavior. Sources include Common Crawl, WebText, OpenWebText, & books.

LLM04: Model Denial of Service

Attackers cause resource-heavy operations on LLMs, leading to service degradation or high costs. The vulnerability is magnified due to the resource-intensive nature of LLMs and unpredictability of user inputs.

LLM05: Supply Chain Vulnerabilities

LLM application lifecycle can be compromised by vulnerable components or services, leading to security attacks. Using third-party datasets, pre-trained models, and plugins can add vulnerabilities.

LLM06: Sensitive Information Disclosure

LLM’s may inadvertently reveal confidential data in its responses, leading to unauthorized data access, privacy violations, and security breaches. It’s crucial to implement data sanitization and strict user policies to mitigate this.

LLM07: Insecure Plugin Design

LLM plugins can have insecure inputs and insufficient access control. This lack of application control makes them easier to exploit and can result in consequences like remote code execution.

LLM08: Excessive Agency

LLM-based systems may undertake actions leading to unintended consequences. The issue arises from excessive functionality, permissions, or autonomy granted to the LLM-based systems.

LLM09: Overreliance

Systems or people overly depending on LLMs without oversight may face misinformation, miscommunication, legal issues, and security vulnerabilities due to incorrect or inappropriate content generated by LLMs.

LLM10: Model Theft

This involves unauthorized access, copying, or exfiltration of proprietary LLM models. The impact includes economic losses, compromised competitive advantage, and potential access to sensitive information.

The organization invites experts to join it and provide support to the project.

You can currently download version 1.0 in two formats.  The full PDF and the abridged slide format.

Follow me on Twitter: @securityaffairs and Facebook and Mastodon

Pierluigi Paganini

(SecurityAffairs – hacking, OWASP Top 10 for LLM)


facebook linkedin twitter

Hacking hacking news information security news IT Information Security Large Language Models LLM OWASP OWASP Top 10 for LLM Pierluigi Paganini Security Affairs Security News

you might also like

Pierluigi Paganini July 04, 2025
Critical Sudo bugs expose major Linux distros to local Root exploits
Read more
Pierluigi Paganini July 04, 2025
Google fined $314M for misusing idle Android users' data
Read more

leave a comment

newsletter

Subscribe to my email list and stay
up-to-date!

    recent articles

    Critical Sudo bugs expose major Linux distros to local Root exploits

    Security / July 04, 2025

    Google fined $314M for misusing idle Android users' data

    Laws and regulations / July 04, 2025

    A flaw in Catwatchful spyware exposed logins of +62,000 users

    Malware / July 04, 2025

    China-linked group Houken hit French organizations using zero-days

    APT / July 03, 2025

    Cybercriminals Target Brazil: 248,725 Exposed in CIEE One Data Breach

    Data Breach / July 03, 2025

    To contact me write an email to:

    Pierluigi Paganini :
    pierluigi.paganini@securityaffairs.co

    LEARN MORE

    QUICK LINKS

    • Home
    • Cyber Crime
    • Cyber warfare
    • APT
    • Data Breach
    • Deep Web
    • Digital ID
    • Hacking
    • Hacktivism
    • Intelligence
    • Internet of Things
    • Laws and regulations
    • Malware
    • Mobile
    • Reports
    • Security
    • Social Networks
    • Terrorism
    • ICS-SCADA
    • POLICIES
    • Contact me

    Copyright@securityaffairs 2024

    We use cookies on our website to give you the most relevant experience by remembering your preferences and repeat visits. By clicking “Accept All”, you consent to the use of ALL the cookies. However, you may visit "Cookie Settings" to provide a controlled consent.
    Cookie SettingsAccept All
    Manage consent

    Privacy Overview

    This website uses cookies to improve your experience while you navigate through the website. Out of these cookies, the cookies that are categorized as necessary are stored on your browser as they are essential for the working of basic functionalities...
    Necessary
    Always Enabled
    Necessary cookies are absolutely essential for the website to function properly. This category only includes cookies that ensures basic functionalities and security features of the website. These cookies do not store any personal information.
    Non-necessary
    Any cookies that may not be particularly necessary for the website to function and is used specifically to collect user personal data via analytics, ads, other embedded contents are termed as non-necessary cookies. It is mandatory to procure user consent prior to running these cookies on your website.
    SAVE & ACCEPT