PYSEC-2026-4290 Pydantic AI: Excessive resource use when local web fetching converts nested HTML

Summary Applications using Pydantic AI's local web-fetch tool can experience excessive CPU and memory use when it converts attacker-controlled HTML. An agent must fetch the affected page; provider-native web fetching is not affected. Details Nested block elements cause HTML-to-Markdown conversion...

PYSEC-2026-4286 Pydantic AI: Event loop blocked by quadratic title extraction in `web_fetch`

Summary The local web-fetch tool webfetchtool, also used as the WebFetch capability's local fallback processed responses with several steps whose running time grows quadratically with the size of certain server-controlled inputs, and ran them on the event loop: decoding the body with whichever...

Pydantic AI: Excessive resource use when local web fetching converts nested HTML

Summary Applications using Pydantic AI's local web-fetch tool can experience excessive CPU and memory use when it converts attacker-controlled HTML. An agent must fetch the affected page; provider-native web fetching is not affected. Details Nested block elements cause HTML-to-Markdown conversion...

GHSA-V36G-JCW9-X7CW Pydantic AI: Excessive resource use when local web fetching converts nested HTML

Summary Applications using Pydantic AI's local web-fetch tool can experience excessive CPU and memory use when it converts attacker-controlled HTML. An agent must fetch the affected page; provider-native web fetching is not affected. Details Nested block elements cause HTML-to-Markdown conversion...

GHSA-FPF4-VWCP-V4HP Pydantic AI: Event loop blocked by quadratic title extraction in `web_fetch`

Summary The local web-fetch tool webfetchtool, also used as the WebFetch capability's local fallback processed responses with several steps whose running time grows quadratically with the size of certain server-controlled inputs, and ran them on the event loop: decoding the body with whichever...

CVE-2026-107287

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 webfetchtool and the WebFetch local fallback can consume excessive CPU and memory during HTML-to-Markdown conversion of attacker-controlled HTML...

CVE-2026-107287

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 webfetchtool and the WebFetch local fallback can consume excessive CPU and memory during HTML-to-Markdown conversion of attacker-controlled HTML...

CVE-2026-107287 Pydantic AI: Excessive resource use when local web fetching converts nested HTML

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 webfetchtool and the WebFetch local fallback can consume excessive CPU and memory during HTML-to-Markdown conversion of attacker-controlled HTML...

CVE-2026-107287 Pydantic AI: Excessive resource use when local web fetching converts nested HTML

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 webfetchtool and the WebFetch local fallback can consume excessive CPU and memory during HTML-to-Markdown conversion of attacker-controlled HTML...

EUVD-2026-95075

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 webfetchtool and the WebFetch local fallback can consume excessive CPU and memory during HTML-to-Markdown conversion of attacker-controlled HTML...

CVE-2026-107287

The Pydantic AI Python agent framework contains a vulnerability where the local web_fetch_tool and WebFetch local fallback exhibit excessive CPU and memory consumption. This is caused by inefficient processing during the HTML-to-Markdown conversion of attacker-controlled HTML containing deeply ne...

CVE-2026-107287: Uncontrolled Resource Consumption

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 webfetchtool and the WebFetch local fallback can consume excessive CPU and memory during HTML-to-Markdown conversion of attacker-controlled HTML...

PT-2026-108032

Name of the Vulnerable Software and Affected Versions Pydantic AI versions 1.77.0 through 1.107.6 Pydantic AI versions prior to 2.52.0 Description The local web fetch tool and the WebFetch local fallback can consume excessive CPU and memory during the conversion of HTML to Markdown. This occurs...

Server-side Request Forgery (SSRF)

Overview misp-modules is a MISP modules are autonomous modules that can be used for expansion and other services in MISP Affected versions of this package are vulnerable to Server-side Request Forgery SSRF in the htmltomarkdown process. An attacker can access internal network resources by supplyi...

EUVD-2026-43306

A Server-Side Request Forgery SSRF protection bypass existed in the htmltomarkdown expansion module of misp-modules. The module attempts to prevent requests to loopback, private, link-local, and other restricted IP address ranges. However, IP addresses were compared against the blocked ranges...

CVE-2026-62143

A Server-Side Request Forgery SSRF protection bypass existed in the htmltomarkdown expansion module of misp-modules. The module attempts to prevent requests to loopback, private, link-local, and other restricted IP address ranges. However, IP addresses were compared against the blocked ranges...

CVE-2026-62143 Server-Side Request Forgery protection bypass in misp-modules html_to_markdown via IPv4-mapped IPv6 addresses

A Server-Side Request Forgery SSRF protection bypass existed in the htmltomarkdown expansion module of misp-modules. The module attempts to prevent requests to loopback, private, link-local, and other restricted IP address ranges. However, IP addresses were compared against the blocked ranges...

CVE-2026-62143

The CVE-2026-62143 issue affects the html_to_markdown expansion module of misp-modules. An SSRF protection bypass occurred because IPv4-mapped IPv6 addresses were not normalised before checking blocked IP ranges, allowing an authenticated attacker to supply addresses like http://[::ffff:127.0.0.1...

CVE-2026-62143 Server-Side Request Forgery protection bypass in misp-modules html_to_markdown via IPv4-mapped IPv6 addresses

A Server-Side Request Forgery SSRF protection bypass existed in the htmltomarkdown expansion module of misp-modules. The module attempts to prevent requests to loopback, private, link-local, and other restricted IP address ranges. However, IP addresses were compared against the blocked ranges...

CVE-2026-44363

MISP modules are autonomous modules that can be used to extend MISP for new services. Prior to 3.0.7, an unsafe remote resource fetching vulnerability existed in MISP Modules expansion modules. The htmltomarkdown module accepted arbitrary HTTPS URLs without sufficient validation, which could allo...