CVE-2026-107289: pydantic-ai · Server-Side Request Forgery (SSRF)
Affects pydantic-aiSource CVE Database V5
Not known to be exploited · CVSS 6.8 Medium : upgrade to 2.44.0 or 1.107.6 when convenient.
Data as of 21 Nov 2026, 17:34 UTC
- EPSS
- 0.3% chance of exploitation in 30 days – higher than 33% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
- Patch
- Available – fixed in 2.44.0, 1.107.6
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:N/A:NExploitation evidence
Disclosed: evidence found.
CVE published 8 Oct 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 21 Nov 2026.
What to do
Upgrade pydantic-ai and pydantic-ai-slim to 2.44.0 or 1.107.6.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| pydanticpydantic-ai | Affected
| Fixed in
|
| pydanticpydantic-ai | Affected
| Fixed in
|
| pydanticpydantic-ai-slim | Affected
| Fixed in
|
| pydanticpydantic-ai-slim | Affected
| Fixed in
|
PyPIpydantic-aipkg:pypi/pydantic-aiOther threats | Affected
| Fixed in
|
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
Upgrade pydantic-ai to version 1.107.6 or later, or 2.44.0 or later, where this vulnerability is fixed. Since the vulnerable features are opt-in and disabled by default, ensure that applications do not enable FileUrl with force_download='allow-local' or web_fetch_tool with allow_local_urls=True unless necessary. Patch status is confirmed fixed in the stated versions.
Description
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.56.0 until 1.107.6 and 2.44.0, applications that opt attacker-influenced URLs into local network access through FileUrl with force_download='allow-local' or web_fetch_tool with allow_local_urls=True can bypass the cloud-metadata blocklist by appending an IPv6 zone identifier to an IPv6 metadata address. IPv6Address equality and hashing include the zone identifier, so the blocklist comparison fails even though the network stack ignores the zone on a non-link-local destination and reaches the metadata service, potentially exposing cloud IAM credentials. The opt-in settings are disabled by default, and the issue requires an IPv6-enabled environment. This issue is fixed in versions 1.107.6 and 2.44.0.
References
- github.com/pydantic/pydantic-ai/security/advisories/GHSA-vmxc-h2x2-jmf3 (opens in a new tab)
- github.com/pydantic/pydantic-ai/pull/8401 (opens in a new tab)
- github.com/pydantic/pydantic-ai/pull/8402 (opens in a new tab)
- github.com/pydantic/pydantic-ai/commit/02157e1b87bd45d3f2e111ce07afdf89f9fb0e5b (opens in a new tab)
- github.com/pydantic/pydantic-ai/commit/4da70591460f51a8c4f128eaeef70a33340dbd55 (opens in a new tab)
- github.com/pydantic/pydantic-ai/releases/tag/v1.107.6 (opens in a new tab)
- github.com/pydantic/pydantic-ai/releases/tag/v2.44.0 (opens in a new tab)