PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-107290 pydantic CVE debrief

Pydantic AI's `web_fetch` tool is vulnerable to a denial-of-service (DoS) attack due to quadratic title extraction. An attacker-controlled page can block the event loop, stalling other agent runs and requests. This issue affects versions 1.77.0 to 1.107.6 and 2.44.0. Defenders should assess exposure and prioritize patching to prevent potential DoS attacks. The vulnerability has a medium severity and is fixed in versions 1.107.6 and 2.44.0. The CVE record and source item provide details on the vulnerability, including affected versions and fixed versions.

Vendor
pydantic
Product
pydantic-ai
CVSS
MEDIUM 6.5
CISA KEV
Not listed in stored evidence
Original CVE published
2026-10-08
Original CVE updated
2026-10-08
Advisory published
2026-10-08
Advisory updated
2026-10-08

Who should care

Defenders responsible for Pydantic AI installations, specifically those using versions 1.77.0 to 1.107.6 and 2.44.0, should assess exposure and prioritize patching to prevent potential DoS attacks.

Why it matters

CVE-2026-107290 is a medium-severity vulnerability in Pydantic AI's `web_fetch` tool that can lead to denial-of-service (DoS) attacks. Defenders should prioritize patching vulnerable versions to prevent potential attacks.

  • Potential denial-of-service (DoS) attacks against Pydantic AI installations
  • Stalling of other agent runs and requests due to blocked event loop
  • Verification of inventory and patching of vulnerable versions required

Technical summary

Pydantic AI's `web_fetch` tool is vulnerable to quadratic title extraction, which can cause the event loop to block, stalling other agent runs and requests. This issue affects versions 1.77.0 to 1.107.6 and 2.44.0, and is fixed in versions 1.107.6 and 2.44.0. The vulnerability has a medium severity and can lead to denial-of-service (DoS) attacks. Defenders should prioritize patching vulnerable versions to prevent potential attacks. The CVE record and source item provide details on the vulnerability, including affected versions and fixed versions.

Defensive priority

Defenders should prioritize patching vulnerable versions of Pydantic AI, specifically versions 1.77.0 to 1.107.6 and 2.44.0, to prevent potential DoS attacks.

Recommended defensive actions

  • Patch vulnerable versions of Pydantic AI to prevent potential DoS attacks
  • Verify inventory of Pydantic AI installations to identify potential exposure
  • Monitor for suspicious activity related to `web_fetch` tool usage
  • Review compensating controls for exposed systems while remediation is scheduled and verified
  • Check relevant monitoring, detection, and logs for exposed assets that need extra review
  • Track exceptions, retest remediated assets, and close the item only after evidence is documented
  • Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up

Evidence notes

The CVE record and source item provide details on the vulnerability, including affected versions (1.77.0 to 1.107.6 and 2.44.0) and fixed versions (1.107.6 and 2.44.0). However, there is limited information on potential exploitation or victim impact. Defenders should verify inventory and patch vulnerable versions to prevent potential DoS attacks. The vulnerability has a medium severity and can lead to denial-of-service (DoS) attacks. There is no evidence of exploitation in the wild, but defenders should monitor for suspicious activity

Sources and references

Verified primary and authoritative sources

  • CVE-2026-107290 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-107290

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-107290 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-107290

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

  • Pydantic AI: Event loop blocked by quadratic title extraction in `web_fetch`

    Unverified legacy reference

    URL: https://raw.githubusercontent.com/CVEProject/cvelistV5/main/cves/2026/107xxx/CVE-2026-107290.json

    cve_program_cvelist_v5

  • Source reference

    Unverified legacy reference

    URL: https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-fpf4-vwcp-v4hp

    Supplemental source - x_refsource_CONFIRM

  • Source reference

    Unverified legacy reference

    URL: https://github.com/pydantic/pydantic-ai/pull/8397

    Supplemental source - x_refsource_MISC

  • Source reference

    Unverified legacy reference

    URL: https://github.com/pydantic/pydantic-ai/pull/8399

    Supplemental source - x_refsource_MISC

  • Source reference

    Unverified legacy reference

    URL: https://github.com/pydantic/pydantic-ai/pull/8418

    Supplemental source - x_refsource_MISC

  • Source reference

    Unverified legacy reference

    URL: https://github.com/pydantic/pydantic-ai/pull/84332

    Supplemental source - x_refsource_MISC

  • Source reference

    Unverified legacy reference

    URL: https://github.com/pydantic/pydantic-ai/pull/8434

    Supplemental source - x_refsource_MISC

  • Source reference

    Unverified legacy reference

    URL: https://github.com/pydantic/pydantic-ai/commit/2faa6181d8a17d83bc9516d035c5270db8730fa0

    Supplemental source - x_refsource_MISC

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.