Abstract
Millions of users leverage generative pretrained transformer (GPT)-based language models developed by leading model providers for a wide range of tasks. To support enhanced user interaction and customization, many platforms- such as OpenAI- now enable developers to create and publish tailored model instances, known as custom GPTs, via dedicated repositories or application stores. These custom GPTs empower users to browse and interact with specialized applications designed to meet specific needs. However, as custom GPTs see growing adoption, concerns regarding their security vulnerabilities have intensified. Existing research on these vulnerabilities remains largely theoretical, often lacking empirical, large-scale, and statistically rigorous assessments of associated risks.
In this study, we analyze 14,904 custom GPTs to assess their susceptibility to seven exploitable threats, such as roleplay-based attacks, system prompt leakage, phishing content generation, and malicious code synthesis, across various categories and popularity tiers within the OpenAI marketplace. We introduce a multi-metric ranking system to examine the relationship between a custom GPT's popularity and its associated security risks.
Our findings reveal that over 95% of custom GPTs lack adequate security protections. The most prevalent vulnerabilities include roleplay-based vulnerabilities (96.51%), system prompt leakage (92.20%), and phishing (91.22%). Furthermore, we demonstrate that OpenAI's foundational models exhibit inherent security weaknesses, which are often inherited or amplified in custom GPTs. These results highlight the urgent need for enhanced security measures and stricter content moderation to ensure the safe deployment of GPT-based applications
In this study, we analyze 14,904 custom GPTs to assess their susceptibility to seven exploitable threats, such as roleplay-based attacks, system prompt leakage, phishing content generation, and malicious code synthesis, across various categories and popularity tiers within the OpenAI marketplace. We introduce a multi-metric ranking system to examine the relationship between a custom GPT's popularity and its associated security risks.
Our findings reveal that over 95% of custom GPTs lack adequate security protections. The most prevalent vulnerabilities include roleplay-based vulnerabilities (96.51%), system prompt leakage (92.20%), and phishing (91.22%). Furthermore, we demonstrate that OpenAI's foundational models exhibit inherent security weaknesses, which are often inherited or amplified in custom GPTs. These results highlight the urgent need for enhanced security measures and stricter content moderation to ensure the safe deployment of GPT-based applications
| Original language | English |
|---|---|
| Pages | 1-17 |
| Number of pages | 17 |
| Publication status | Submitted - 15 May 2025 |
| Event | International Symposium on Research in Attacks, Intrusions, and Defenses - Gold Coast, Australia, Gold Coast, Australia Duration: 19 Oct 2025 → 22 Oct 2025 Conference number: 28 https://raid2025.github.io/ |
Conference
| Conference | International Symposium on Research in Attacks, Intrusions, and Defenses |
|---|---|
| Abbreviated title | RAID |
| Country/Territory | Australia |
| City | Gold Coast |
| Period | 19/10/25 → 22/10/25 |
| Internet address |