Lucene search
+L

122 matches found

EUVD
EUVD
•added 2026/10/08 5:40 p.m.•1 views

EUVD-2026-95075

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

6.5CVSS
SaveExploits0References7
OSV
OSV
•added 2026/10/08 5:16 p.m.•1 views

GHSA-H4XC-3QFQ-JF93 Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint

Summary The Pydantic AI development web chat UI Agent.toweb, clai web did not check the content type of requests to its chat endpoint. This allowed a website visited by a developer to submit a request to a chat UI running on that developer's machine, causing the served agent to run and to execute...

7.6CVSS
SaveExploits0References8
Cvelist
Cvelist
•added 2026/10/08 5:02 p.m.•2 views

CVE-2026-107295 `pydantic-ai-slim` web UI `/api/chat` accepts browser-simple cross-origin requests that can trigger agent tool execution

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 1.107.4 and 2.28.0, the Agent.toweb and clai web development chat endpoint has missing request content-type validation. A website visited by a developer can submit a...

7.6CVSS
SaveExploits0References7
Cvelist
Cvelist
•added 2026/10/08 4:59 p.m.•1 views

CVE-2026-107294 Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.2 and 2.24.0, webfetchtool, the WebFetch local fallback, and remote FileUrl media downloads buffer the complete HTTP response body before enforcing content-size controls. An...

6.5CVSS
SaveExploits0References7
Cvelist
Cvelist
•added 2026/10/08 4:57 p.m.•4 views

CVE-2026-107293 Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.3.4 until 1.107.4 and 2.27.1, OpenTelemetry instrumentation configured with InstrumentationSettingsincludecontent=False can export retry prompts outside tool calls in genai.input.messages an...

2.3CVSS
SaveExploits0References4
CVE
CVE
•added 2026/10/08 4:57 p.m.•2 views

CVE-2026-107293

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.3.4 until 1.107.4 and 2.27.1, OpenTelemetry instrumentation configured with InstrumentationSettingsincludecontent=False can export retry prompts outside tool calls in genai.input.messages an...

2.3CVSS
SaveExploits0References4
Cvelist
Cvelist
•added 2026/10/08 4:26 p.m.•1 views

CVE-2026-107292 Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the local chat endpoint does not validate the `Host` header

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 2.30.0, the Agent.toweb and clai web development chat server does not validate the Host header, allowing a website visited by a developer to use DNS rebinding to reach a...

6.4CVSS
SaveExploits0References7
CVE
CVE
•added 2026/10/08 4:26 p.m.•2 views

CVE-2026-107292

The Pydantic AI Python agent framework is vulnerable in versions 1.34.0 through 2.30.0 due to a lack of Host header validation in the Agent.to_web() and clai web development chat servers. An attacker can leverage DNS rebinding from a malicious website to bypass Origin checks and CSRF tokens , acc...

6.4CVSS6AI score
SaveExploits0References7
Cvelist
Cvelist
•added 2026/10/08 4:22 p.m.•2 views

CVE-2026-107291 Pydantic AI OpenTelemetry instrumentation: exception events on tool and agent run spans include content when `include_content=False`

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.3.4 until 1.107.6 and 2.44.0, OpenTelemetry instrumentation configured with InstrumentationSettingsincludecontent=False can still export sensitive agent content through exception.message and...

2.3CVSS
SaveExploits0References13
CVE
CVE
•added 2026/10/08 4:22 p.m.•3 views

CVE-2026-107291

The Pydantic AI Python agent framework is vulnerable to sensitive information disclosure in versions 0.3.4 through 1.107.6 and 2.44.0 . When OpenTelemetry instrumentation is configured with include_content=False, the system fails to redact sensitive agent content from exception.message and except...

2.3CVSS5.9AI score
SaveExploits0References13
NVD
NVD
•added 2026/10/08 4:17 p.m.•0 views

CVE-2026-107288

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.6 and 2.44.0, the local webfetchtool and the WebFetch local fallback compare blockeddomains entries with a URL hostname before both values are normalized to the form used by...

3.7CVSS
SaveExploits0References9
NVD
NVD
•added 2026/10/08 4:17 p.m.•1 views

CVE-2026-107289

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 forcedownload='allow-local' or webfetchtool with...

6.8CVSS
SaveExploits0References7
NVD
NVD
•added 2026/10/08 4:17 p.m.•0 views

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...

6.5CVSS
SaveExploits0References7
CVE
CVE
•added 2026/10/08 4:09 p.m.•2 views

CVE-2026-107290

The Pydantic AI Python agent framework is vulnerable to a denial-of-service condition in the local web_fetch_tool and the WebFetch local fallback process. Specifically, versions 1.77.0 to 1.107.6 and 2.44.0 exhibit quadratic title extraction , whitespace normalization, and ordered-list numbering ...

6.5CVSS5.8AI score
SaveExploits0References13
Cvelist
Cvelist
•added 2026/10/08 4:09 p.m.•1 views

CVE-2026-107290 Pydantic AI: Event loop blocked by quadratic title extraction in `web_fetch`

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.6 and 2.44.0, the local webfetchtool and the WebFetch local fallback process server-controlled responses with quadratic title extraction, whitespace normalization, and...

6.5CVSS
SaveExploits0References13
Cvelist
Cvelist
•added 2026/10/08 3:20 p.m.•6 views

CVE-2026-107289 Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv6 zone identifier (incomplete fix for CVE-2026-46678 and CVE-2026-48782)

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 forcedownload='allow-local' or webfetchtool with...

6.8CVSS
SaveExploits0References7
EUVD
EUVD
•added 2026/10/08 3:20 p.m.•1 views

EUVD-2026-95077

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 forcedownload='allow-local' or webfetchtool with...

6.8CVSS
SaveExploits0References7
CVE
CVE
•added 2026/10/08 3:20 p.m.•4 views

CVE-2026-107289

The Pydantic AI Python agent framework is vulnerable to Server-Side Request Forgery (SSRF) in versions 1.56.0 through 1.107.5 and 2.44.0. When users opt-in to local network access via FileUrl (with force_download='allow-local') or web_fetch_tool (with allow_local_urls=True), an attacker can bypas...

6.8CVSS5.8AI score
SaveExploits0References7
Cvelist
Cvelist
•added 2026/10/08 3:18 p.m.•5 views

CVE-2026-107288 Pydantic AI: web_fetch_tool blocked_domains bypass via a hostname the resolver normalizes differently

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.6 and 2.44.0, the local webfetchtool and the WebFetch local fallback compare blockeddomains entries with a URL hostname before both values are normalized to the form used by...

3.7CVSS
SaveExploits0References9
CVE
CVE
•added 2026/10/08 3:18 p.m.•5 views

CVE-2026-107288

The Pydantic AI Python agent framework versions 1.77.0 through 1.107.6 and 2.44.0 are vulnerable to a Server-Side Request Forgery (SSRF) . The root cause is that the web_fetch_tool and WebFetch local fallback compare blocked_domains entries against a URL hostname before both values are normalized...

3.7CVSS5.8AI score
SaveExploits0References9
Rows per page
Query Builder