Technology · Pydantic
Pydantic AI vulnerabilities
Updated . Rebuilt every hour.
Junglewise Threat Intelligence has tracked 9 vulnerabilities in Pydantic AI: 0 in the last 7 days and 9 in the last 90 days, 0 of them critical and 0 exploited in the wild. The most recent, CVE-2026-107286, was published on 8 October 2026. Nothing in the last four weeks, down from 9 vulnerabilities in the four before.
- Last 7 days
- 0
- Last 90 days
- 9
- Critical, all time
- 0
- Exploited in the wild
- 0
About Pydantic AI
Python library for building AI agents with type-safe tool calling and structured outputs.
Latest Pydantic AI vulnerabilities
- CVE-2026-107286: Pydantic AI concurrency slot leak in streamed requestshighCVSS 7.5EPSS 0.4%
- CVE-2026-107287: Pydantic AI excessive resource consumption in HTML-to-Markdown conversionmediumCVSS 6.5EPSS 0.3%
- CVE-2026-107292: Pydantic AI web chat UI Host header validation bypassmediumCVSS 6.4EPSS 0.1%
- CVE-2026-107295: Pydantic AI missing content-type validation in chat endpointhighCVSS 7.6EPSS 0.2%
- CVE-2026-107293: Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`mediumCVSS 4EPSS 0.3%
- CVE-2026-107294: Pydantic AI unbounded memory use in remote content downloadmediumCVSS 6.5EPSS 0.4%
- CVE-2026-107290: Pydantic AI event loop blocking in web_fetch title extractionmediumCVSS 6.5EPSS 0.4%
- CVE-2026-107291: Pydantic AI OpenTelemetry instrumentation content disclosure with include_content=FalsemediumCVSS 4EPSS 0.5%
- CVE-2026-107289: Pydantic AI SSRF in cloud-metadata blocklist bypass via IPv6 zone identifiersmediumCVSS 6.8EPSS 0.3%
Most severe Pydantic AI vulnerabilities
Exploited in the wild first, then by severity and CVSS score.
- CVE-2026-107295: Pydantic AI missing content-type validation in chat endpointhighCVSS 7.6EPSS 0.2%
- CVE-2026-107286: Pydantic AI concurrency slot leak in streamed requestshighCVSS 7.5EPSS 0.4%
- CVE-2026-107289: Pydantic AI SSRF in cloud-metadata blocklist bypass via IPv6 zone identifiersmediumCVSS 6.8EPSS 0.3%
- CVE-2026-107294: Pydantic AI unbounded memory use in remote content downloadmediumCVSS 6.5EPSS 0.4%
- CVE-2026-107290: Pydantic AI event loop blocking in web_fetch title extractionmediumCVSS 6.5EPSS 0.4%
- CVE-2026-107287: Pydantic AI excessive resource consumption in HTML-to-Markdown conversionmediumCVSS 6.5EPSS 0.3%
- CVE-2026-107292: Pydantic AI web chat UI Host header validation bypassmediumCVSS 6.4EPSS 0.1%
- CVE-2026-107291: Pydantic AI OpenTelemetry instrumentation content disclosure with include_content=FalsemediumCVSS 4EPSS 0.5%
- CVE-2026-107293: Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`mediumCVSS 4EPSS 0.3%
Vulnerabilities per week
Nothing in the last four weeks, down from 9 vulnerabilities in the four before. The last 13 weeks, by the week each vulnerability was published.
| Week of | Bar | Vulns | Critical |
|---|---|---|---|
| 17 Aug 2026 | 0 | 0 | |
| 24 Aug 2026 | 0 | 0 | |
| 31 Aug 2026 | 0 | 0 | |
| 7 Sep 2026 | 0 | 0 | |
| 14 Sep 2026 | 0 | 0 | |
| 21 Sep 2026 | 0 | 0 | |
| 28 Sep 2026 | 0 | 0 | |
| 5 Oct 2026 | 9 | 0 | |
| 12 Oct 2026 | 0 | 0 | |
| 19 Oct 2026 | 0 | 0 | |
| 26 Oct 2026 | 0 | 0 | |
| 2 Nov 2026 | 0 | 0 | |
| 9 Nov 2026 | 0 | 0 |
Embed a badge
A live badge for a README, a status page or an internal wiki: how many Pydantic AI vulnerabilities were published in the last 7 days and how many of them are critical, refreshed hourly.
[](https://junglewise.ai/threats/technologies/pydantic-pydantic-ai)<a href="https://junglewise.ai/threats/technologies/pydantic-pydantic-ai"><img src="https://junglewise.ai/threats/technologies/pydantic-pydantic-ai/badge.svg" alt="Pydantic AI vulnerabilities" /></a>How this is built
Junglewise Threat Intelligence collects vulnerabilities from NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories, and matches each one to the technologies and vendors it affects. Dates are the date a vulnerability was published, in UTC.
The pages are rebuilt from the database every hour. Frozen weekly and monthly reports never change once published, so they can be cited.
Use this data
The same data is at https://junglewise.ai/threats/technologies/pydantic-pydantic-ai.json, and this page as text at https://junglewise.ai/threats/technologies/pydantic-pydantic-ai.md, for scripts and language models. It is free to reuse under CC BY 4.0 with a link back to this page.
Cite as: Junglewise Threat Intelligence, "Pydantic AI vulnerabilities", https://junglewise.ai/threats/technologies/pydantic-pydantic-ai, 9 November 2026.