CVE-2026-34936
Received Received - Intake
Server-Side Request Forgery in PraisonAI passthrough Functions

Publication date: 2026-04-03

Last updated on: 2026-04-14

Assigner: GitHub, Inc.

Description
PraisonAI is a multi-agent teams system. Prior to version 4.5.90, passthrough() and apassthrough() in praisonai accept a caller-controlled api_base parameter that is concatenated with endpoint and passed directly to httpx.Client.request() when the litellm primary path raises AttributeError. No URL scheme validation, private IP filtering, or domain allowlist is applied, allowing requests to any host reachable from the server. This issue has been patched in version 4.5.90.
CVSS Scores
EPSS Scores
Probability:
Percentile:
Meta Information
Published
2026-04-03
Last Modified
2026-04-14
Generated
2026-06-16
AI Q&A
2026-04-04
EPSS Evaluated
2026-06-15
NVD
Affected Vendors & Products
Showing 1 associated CPE
Vendor Product Version / Range
praison praisonai to 4.5.90 (exc)
Helpful Resources
Exploitability
CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-918 The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.
Attack-Flow Graph
AI Quick Actions
Instant insights powered by AI
Executive Summary

The vulnerability exists in PraisonAI versions prior to 4.5.90, specifically in the passthrough() and apassthrough() functions. These functions accept a caller-controlled api_base parameter, which is concatenated with an endpoint and passed directly to httpx.Client.request() when a certain error occurs. There is no validation of the URL scheme, no filtering of private IP addresses, and no domain allowlist applied. This means an attacker can make requests to any host reachable from the server, potentially abusing the system to access unauthorized network resources.

Impact Analysis

This vulnerability can allow an attacker with limited privileges to make arbitrary HTTP requests from the server to any reachable host. Because there is no restriction on the destination, it could be used to access internal or private network resources that are normally inaccessible, potentially leading to information disclosure or unauthorized network interactions. The CVSS score of 7.7 indicates a high severity impact on confidentiality.

Mitigation Strategies

The vulnerability has been patched in PraisonAI version 4.5.90. The immediate step to mitigate this vulnerability is to upgrade PraisonAI to version 4.5.90 or later.

Compliance Impact

The vulnerability allows an attacker to make arbitrary HTTP requests from the server to any host reachable from it, due to lack of URL scheme validation, private IP filtering, or domain allowlisting.

This could potentially lead to unauthorized data access or data exfiltration, which may impact compliance with standards and regulations such as GDPR or HIPAA that require protection of sensitive data and prevention of unauthorized access.

However, the provided information does not explicitly describe the direct impact on compliance with these standards.

Chat Assistant
Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-34936. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70
EPSS Chart