CVE-2026-107287— Pydantic AI: Excessive resource use when local web fetching converts nested HTML
Quick assessment
Affected
pydantic pydantic-ai
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.
Pydantic AI 是一个用于构建生成式 AI 应用和工作流的 Python 智能体（Agent）框架。在版本 1.77.0 至 1.107.7 以及 2.52.0 之前，本地使用的 和 WebFetch 本地回退机制在处理攻击者控制的 HTML 时，在将 HTML 转换为 Markdown 的过程中会消耗过量的 CPU 和内存。这些 HTML 文件通常包含深层嵌套的块级元素。转换过程会反复重新处理已累积的文本内容，并且在应用返回内容长度限制之前，中间输出结果可能大幅膨胀，从而导致由模型发起的网络请求延迟进程中
Possible ATT&CK Techniques 1 AI
T1496 · Resource HijackingAffected Version Matrix 4
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| pydantic | pydantic-ai | >= 1.77.0, < 1.107.7 |
affected |
>= 2.0.0b1, < 2.52.0 |
affected | ||
| pydantic | pydantic-ai-slim | >= 1.77.0, < 1.107.7 |
affected |
>= 2.0.0b1, < 2.52.0 |
affected |
Get alerts for future matching vulnerabilities
Log in to subscribe
I. Basic Information for CVE-2026-107287
Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
Vulnerability Title
Pydantic AI: Excessive resource use when local web fetching converts nested HTML
Source: CVE Program / CVE List V5
Vulnerability Description
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.7 and 2.52.0, the local web_fetch_tool and the WebFetch local fallback can consume excessive CPU and memory during HTML-to-Markdown conversion of attacker-controlled HTML containing deeply nested block elements. Conversion repeatedly reprocesses accumulated text and can greatly expand intermediate output before the returned-content limit is applied, allowing a model-directed fetch to delay other work in the process. Provider-native web fetching is not affected. This issue is fixed in versions 1.107.7 and 2.52.0.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
未加控制的资源消耗(资源穷尽)
Source: CVE Program / CVE List V5
Affected Products
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| pydantic | pydantic-ai | >= 1.77.0, < 1.107.7 | - |
|
| pydantic | pydantic-ai-slim | >= 1.77.0, < 1.107.7 | - |
|
II. Public POCs for CVE-2026-107287
| # | POC Description | Source Link | Shenlong Link |
|---|
AI-Generated POC
Premium
No public POC found.
Login to generate AI POCIII. Intelligence Information for CVE-2026-107287
请登录查看更多情报信息。
Patches & Fixes for CVE-2026-107287 (1)
Vendor Advisories for CVE-2026-107287 (1)
Vendor Pages for CVE-2026-107287 (2)
-
🔗 Release v2.52.0 (2026-09-29) · pydantic/pydantic-ai · GitHub x_refsource_MISC
-
🔗 Release v1.107.7 (2026-09-29) · pydantic/pydantic-ai · GitHub x_refsource_MISC
Same Patch Batch · pydantic · 2026-10-08 · 10 CVEs total
| CVE-2026-107295 | 7.6 HIGH | `pydantic-ai-slim` web UI `/api/chat` accepts browser-simple cross-origin requests that ca |
| CVE-2026-107286 | 7.5 HIGH | Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends e |
| CVE-2026-107289 | 6.8 MEDIUM | Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv6 zone identifier (incomplete fix |
| CVE-2026-107290 | 6.5 MEDIUM | Pydantic AI: Event loop blocked by quadratic title extraction in `web_fetch` |
| CVE-2026-107294 | 6.5 MEDIUM | Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl |
| CVE-2026-107292 | 6.4 MEDIUM | Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the local chat endpoint does not v |
| CVE-2026-107288 | 3.7 LOW | Pydantic AI: web_fetch_tool blocked_domains bypass via a hostname the resolver normalizes |
| CVE-2026-107291 | 2.3 LOW | Pydantic AI OpenTelemetry instrumentation: exception events on tool and agent run spans in |
| CVE-2026-107293 | 2.3 LOW | Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `incl |
IV. Related Vulnerabilities
Same product: pydantic-ai
-
CVE-2026-107295
`pydantic-ai-slim` web UI `/api/chat` accepts browser-simple -
CVE-2026-107294
Pydantic AI: Unbounded memory use when downloading remote co -
CVE-2026-107293
Pydantic AI OpenTelemetry instrumentation: retry prompt cont -
CVE-2026-107292
Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the -
CVE-2026-107291
Pydantic AI OpenTelemetry instrumentation: exception events
Same vendor: pydantic
-
CVE-2026-107295
`pydantic-ai-slim` web UI `/api/chat` accepts browser-simple -
CVE-2026-107294
Pydantic AI: Unbounded memory use when downloading remote co -
CVE-2026-107293
Pydantic AI OpenTelemetry instrumentation: retry prompt cont -
CVE-2026-107292
Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the -
CVE-2026-107291
Pydantic AI OpenTelemetry instrumentation: exception events
Same weakness: CWE-400
-
CVE-2026-107727
Strawberry legacy graphql-ws retains naturally completed sub -
CVE-2026-107391
music-metadata: MP4 stsd sample-entry size==0 causes a synch -
CVE-2026-84276
IBM Guardium Data Protection Denial of Service -
CVE-2026-107294
Pydantic AI: Unbounded memory use when downloading remote co -
CVE-2026-61801
github.com/moby/sys/user has a possible DoS via unbounded pa
V. Comments for CVE-2026-107287
No comments yet