CVE-2024-6331

Affects: prompt injection

CVSS: HIGH · 7.5v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Published: 2024-08-04
Weakness: CWE-74, CWE-74
Source: nvd.nist.gov/vuln/detail/CVE-2024-6331

Description

stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read (LFI) by Prompt Injection. The integration of Google Gimini 1.0 Pro with HarmBlockThreshold.BLOCK_NONE for HarmCategory.HARM_CATEGORY_HATE_SPEECH and HarmCategory.HARM_CATEGORY_HARASSMENT in safety_settings disables content protection. This allows malicious commands to be executed, such as reading sensitive file contents like /etc/passwd.

References

https://huntr.com/bounties/d5ac1051-22fa-42f0-8d82-73267482e60f

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2024-6331 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming