Protect AI Releases 'Bug Bounty' Report On September Vulnerabilities

The vulnerabilities involve tools used to build machine language models that fuel artificial intelligence applications.

Protect AI, which offers artificial intelligence application security, just released its September vulnerability report.

The report was created with Protect AI’s AI/ML “bug bounty” program, huntr. According to the company, the huntr community is made up of over 15,000 members who hunt for vulnerabilities across the “entire OSS AI/ML supply chain.”

The vulnerabilities involve tools used to build ML models that fuel AI applications. These tools are open source and are heavily downloaded to build enterprise AI solutions, Protect AI said in a news release.

This month, the huntr community along with Protect AI researchers, discovered 20 vulnerabilities, some of which allow bad actors to perform complete system takeovers.

Here is a list of some of the major vulnerabilities huntr discovered in September (description quotes from ProtectAI):

Remote Code Execution (RCE) in BerriAI/litellm:

“An attacker can execute arbitrary code on the server by injecting malicious environment variables. The vulnerability occurs in the litellm.get_secret() function, where untrusted data can be passed to the eval function without proper sanitization. This can be exploited by updating environment variables via the /config/update endpoint, allowing an attacker to inject malicious code.”

Insecure Password Reset Token Handling in lunary-ai/lunary

“An attacker can reuse a password reset token to change the victim’s password multiple times.

The vulnerability lies in the password reset functionality, where the token is not invalidated after the password is changed. This allows an attacker who has compromised the token to reuse it and change the password repeatedly.”

Server-Side Request Forgery (SSRF) in gradio-app/gradio

“An attacker can make unauthorized HTTP requests to internal services, potentially accessing sensitive information. The vulnerability is in the save_url_to_cache function, which does not properly validate the path parameter. This allows an attacker to supply a URL that the server will fetch, leading to SSRF.”

Here is the full list of vulnerabilities. Click on the links for recommended fixes and more information on each: