Pydantic AI up to 1.107.6/2.51.x WebFetch resource consumption

Summaryinfo

A vulnerability has been found in Pydantic AI up to 1.107.6/2.51.x and classified as problematic. This affects an unknown function of the component WebFetch. Performing a manipulation results in resource consumption. This vulnerability is reported as CVE-2026-107287. The attack is possible to be carried out remotely. No exploit exists. The affected component should be upgraded.

Detailsinfo

A vulnerability classified as problematic has been found in Pydantic AI up to 1.107.6/2.51.x. This affects an unknown part of the component WebFetch. The manipulation with an unknown input leads to a resource consumption vulnerability. CWE is classifying the issue as CWE-400. The product does not properly control the allocation and maintenance of a limited resource, thereby enabling an actor to influence the amount of resources consumed, eventually leading to the exhaustion of available resources. This is going to have an impact on availability. The summary by CVE is:

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.

It is possible to read the advisory at github.com. This vulnerability is uniquely identified as CVE-2026-107287 since 10/07/2026. The exploitability is told to be easy. It is possible to initiate the attack remotely. No form of authentication is needed for exploitation. It demands that the victim is doing some kind of user interaction. The technical details are unknown and an exploit is not publicly available. The attack technique deployed by this issue is T1499 according to MITRE ATT&CK.

Upgrading to version 1.107.7 or 2.52.0 eliminates this vulnerability.

Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• Pydantic

Name

• AI

Version

• 1.107.0
• 1.107.1
• 1.107.2
• 1.107.3
• 1.107.4
• 1.107.5
• 1.107.6
• 2.0
• 2.1
• 2.2
• 2.3
• 2.4
• 2.5
• 2.6
• 2.7
• 2.8
• 2.9
• 2.10
• 2.11
• 2.12
• 2.13
• 2.14
• 2.15
• 2.16
• 2.17
• 2.18
• 2.19
• 2.20
• 2.21
• 2.22
• 2.23
• 2.24
• 2.25
• 2.26
• 2.27
• 2.28
• 2.29
• 2.30
• 2.31
• 2.32
• 2.33
• 2.34
• 2.35
• 2.36
• 2.37
• 2.38
• 2.39
• 2.40
• 2.41
• 2.42
• 2.43
• 2.44
• 2.45
• 2.46
• 2.47
• 2.48
• 2.49
• 2.50
• 2.51

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Discussion