Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911663508160512 |
|---|---|
| author | Chen, Zhiyang Saba, Tara Deng, Xun Si, Xujie Long, Fan |
| author_facet | Chen, Zhiyang Saba, Tara Deng, Xun Si, Xujie Long, Fan |
| contents | Large Language Models have become critical to modern software development, but their reliance on uncurated web-scale datasets for training introduces a significant security risk: the absorption and reproduction of malicious content. This risk materialized in November 2024, when a user suffered a 2,500 USD financial loss after executing code generated by ChatGPT that contained a live scam phishing URL. To systematically evaluate this risk, we introduce Scam2Prompt, a scalable automated auditing framework that identifies the underlying intent of a scam site and then synthesizes developer-style prompts that mirror this intent, allowing us to test whether an LLM will generate malicious code in response to these prompts. In a large-scale study of four production LLMs (GPT-4o, GPT-4o-mini, Llama-4-Scout, and DeepSeek-V3), we found that Scam2Prompt's developer-style prompts triggered malicious URL generation in 4.24\% of cases. To test the persistence of this security risk, we constructed Innoc2Scam-bench, a benchmark of 1,377 prompts that consistently elicited malicious code from all four initial LLMs. When applied to seven additional production LLMs released in 2025, we found the vulnerability is not only present but severe, with malicious code generation rates ranging from 12.9\% to 47.3\%. Furthermore, existing safety measures like state-of-the-art guardrails or RAG-based agents proved insufficient to prevent this behavior. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_02372 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs Chen, Zhiyang Saba, Tara Deng, Xun Si, Xujie Long, Fan Cryptography and Security Artificial Intelligence Software Engineering Large Language Models have become critical to modern software development, but their reliance on uncurated web-scale datasets for training introduces a significant security risk: the absorption and reproduction of malicious content. This risk materialized in November 2024, when a user suffered a 2,500 USD financial loss after executing code generated by ChatGPT that contained a live scam phishing URL. To systematically evaluate this risk, we introduce Scam2Prompt, a scalable automated auditing framework that identifies the underlying intent of a scam site and then synthesizes developer-style prompts that mirror this intent, allowing us to test whether an LLM will generate malicious code in response to these prompts. In a large-scale study of four production LLMs (GPT-4o, GPT-4o-mini, Llama-4-Scout, and DeepSeek-V3), we found that Scam2Prompt's developer-style prompts triggered malicious URL generation in 4.24\% of cases. To test the persistence of this security risk, we constructed Innoc2Scam-bench, a benchmark of 1,377 prompts that consistently elicited malicious code from all four initial LLMs. When applied to seven additional production LLMs released in 2025, we found the vulnerability is not only present but severe, with malicious code generation rates ranging from 12.9\% to 47.3\%. Furthermore, existing safety measures like state-of-the-art guardrails or RAG-based agents proved insufficient to prevent this behavior. |
| title | Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs |
| topic | Cryptography and Security Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2509.02372 |