Vulnerability · Published Apr 3, 2026 · Assigned by GitHub_M
CVE-2026-34936PraisonAI: SSRF via Unvalidated api_base in passthrough() Fallback
High 7.7
In plain English
A high-severity server-side request forgery in PraisonAI from MervinPraison. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 29% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official 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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | praisonai | 4.5.90 | GHSA-x6m9-gxvr-7jpv |
| PyPI | praisonai | 4.5.90 | PYSEC-2026-2924 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| MervinPraison | PraisonAI | < 4.5.90 |
Weakness: CWE-918 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N