Remote Code Execution via Prompt Injection in vanna-ai/vanna
CVE-2024-5826

9.8CRITICAL

Key Information:

Vendor

Vanna-ai

Status
Vanna-ai/vanna
Vendor
CVE Published:
27 June 2024

What is CVE-2024-5826?

The Vanna AI product experiences a vulnerability allowing for remote code execution due to prompt injection within the vanna.ask function. This issue stems from an absence of sandboxing when executing code generated by language models. As a result, untrusted input can manipulate the code executed through the exec function in src/vanna/base/base.py. An attacker can exploit this vulnerability to achieve remote code execution on the backend server of the application, which may lead to full server compromise.

Affected Version(s)

vanna-ai/vanna <= unspecified

References

https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30...

EPSS Score

7% chance of being exploited in the next 30 days.

CVSS V3.1

Score:
9.8
Severity:
CRITICAL
Confidentiality:
High
Integrity:
High
Availability:
High
Attack Vector:
Network
Attack Complexity:
Low
Privileges Required:
None
User Interaction:
None
Scope:
Unchanged

CVSS V3.0

Score:
9.8
Severity:
CRITICAL
Confidentiality:
High
Integrity:
High
Availability:
High
Attack Vector:
Network
Attack Complexity:
Low
Privileges Required:
None
User Interaction:
None
Scope:
Unchanged

Timeline

  • Vulnerability published

.