.png)
Vulnerable Code Scanner analyzes AI-generated code, preventing harmful outputs from being used by developers
Company expands platform to support Cursor, delivering full protection for AI code assistants
NEW YORK CITY, April 23, 2025 – Prompt Security, a leader in generative AI (GenAI) security, today announced the beta launch of Vulnerable Code Scanner, an advanced security feature that catches potential risks in AI-generated source code before they can pose a threat to enterprises. By automatically scanning AI-generated code, Vulnerable Code Scanner helps ensure that developers don’t use hazardous code suggestions coming from GenAI applications.
Over the course of Q1 this year, Prompt Security released new and enhanced capabilities designed to prevent the exfiltration of organizations’ secrets, PII and IP – a major risk associated with unrestricted developer access to AI code assistants. Now, by scanning AI-generated responses to block malicious code before it makes its way to developers, Vulnerable Code Scanner complements these earlier solution enhancements, offering organizations a full spectrum of protection between developers, LLMs and codebases.
Vulnerable Code Scanner detects risks in AI-generated code suggestions and provides actionable mitigations to help developers understand and fix issues. It notifies security administrators when developers send code to AI code assistants and when they receive vulnerable AI-generated responses. This gives administrators a complete audit trail of exchanges between developers and GenAI applications.
“Given the extent to which developers are increasingly copying code from AI tools, being able to scan AI-generated code outputs is especially important,” said Itamar Golan, CEO and co-founder of Prompt Security. “Alongside our capabilities for preventing data leakage from the developers’ end, Vulnerable Code Scanner is the puzzle piece that makes our coding protection more comprehensive.”
Vulnerable Code Scanner already supports ChatGPT, Microsoft Copilot, Gemini, Claude, Perplexity, Mistral, Grok and DeepSeek. Prompt Security plans a gradual roll out for GitHub Copilot, Tabnine and the other AI code assistants it supports. The solution works for almost 30 programming languages.
As part of its commitment to delivering the most comprehensive AI security solution, Prompt Security is also announcing today its support for Cursor, the popular AI code assistant. From this point forward, Cursor will come under the umbrella of automatic redaction of sensitive information and all other Prompt Security capabilities for AI code assistants.
To learn more about Prompt Security’s capabilities at the RSA Conference in San Francisco, schedule an onsite meeting now for April 28 - May 1, 2025.
About Prompt Security
Founded in August 2023, Prompt Security delivers a complete solution for all generative AI security in the enterprise. Its platform supports millions of prompts and thousands of users every month. The founding team combines deep expertise in both cybersecurity and AI, with years of experience building and securing machine learning systems at organizations like Check Point, Orca Security, and Israel’s elite intelligence unit 8200. Prompt Security’s CEO Itamar Golan was on the OWASP Top 10 for LLM Applications core team and Prompt Security’s CTO & co-founder Lior Drihem contributed to the project. The Prompt Security team of researchers has created proprietary LLMs and developed novel patent-pending techniques for detecting generative AI threats and addressing the associated risks.