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.to_web() and clai web development chat endpoint has missing request content-type validation. A website visited by a developer can submit a browser-compatible request to a loopback-hosted chat server, causing the served agent to run and execute tools with the privileges and credentials of the local process; client-relayed approval decisions also leave requires_approval=True tools exposed. Binding to localhost does not prevent a browser page from reaching the loopback address. This issue is fixed in versions 1.107.4 and 2.28.0.
CVE-2026-107295
This high-severity CVE scores 7.6 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.2% (4th percentile of EPSS-scored CVEs). GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).
- High severity, but no confirmed exploitation yet
A fix is available — apply it.
- CVSS v3
- 7.6
- EG Score
- 7.6HIGHmedium confidence
- EG Risk
- 34EG Risk 34/100CISA SSVC
EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).
How it’s computedSeverity76% × 45%Exploitation0% × 40%Automatability0% × 15%CISA SSVC: Track at every mission impact level.Action: A fix is available. Apply it within your standard update timelines. - EPSS PROB
- 0.2%
- EPSS %ILE
- 4th
- KEV
- Not listed
CISA SSVCTrack at every mission impact level.
A fix is available. Apply it within your standard update timelines.
Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). Mission impact is CISA's Mission & Well-being decision point, and only you can judge it: high means the affected system is essential to your organisation's mission, or its compromise could cause irreversible harm to people. CISA's decision table
Published
October 8, 2026
Last Modified
October 8, 2026
Advisory Details (7)
Auto-updated Oct 8, 2026Web 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 · Advisory · pydantic/pydantic-ai · GitHub
https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h4xc-3qfq-jf93v2.28.0 (2026-08-11)
Patch available: pydantic/pydantic-ai v2.28.0
https://github.com/pydantic/pydantic-ai/releases/tag/v2.28.0v1.107.4 (2026-08-11)
Patch available: pydantic/pydantic-ai v1.107.4
https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.4Only accept JSON request bodies on the web UI chat endpoint (v1 backport)
Fix merged in pydantic/pydantic-ai PR #7383 on 2026-08-11 — awaiting tagged release
https://github.com/pydantic/pydantic-ai/pull/7383Only accept JSON request bodies on the web UI chat endpoint
Patch available: pydantic/pydantic-ai v2.32.0 (PR #7382 merged 2026-08-11)
https://github.com/pydantic/pydantic-ai/pull/7382commit dd2abbdfa029 (pydantic/pydantic-ai)
Fix landed in pydantic/pydantic-ai commit dd2abbdfa029 — awaiting tagged release
https://github.com/pydantic/pydantic-ai/commit/dd2abbdfa029c9ad138e7cc0edd2eaeaf9ed69c0commit d2690201a183 (pydantic/pydantic-ai)
Patch available: pydantic/pydantic-ai v2.32.0 (contains commit d2690201a183)
https://github.com/pydantic/pydantic-ai/commit/d2690201a1834005d382dbf5c47e0ed94ef8bf46Vendor Advisories for CVE-2026-107295(1)
These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.
Affected Packages
(2 across 1 ecosystem)
PyPI(2)
| Package | Vulnerable range | Fix by version range | Dependents |
|---|---|---|---|
| pydantic-ai | 1.100.0 ... 1.99.0 (82 versions) |
| — |
| pydantic-ai-slim | 1.100.0 ... 1.99.0 (82 versions) |
| — |
Weakness Classification(1)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 7× in last 7d / 7× in last 30d)
Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.
- 2026-10-09 20:17 UTCEG score recompute
- 2026-10-09 20:06 UTCEPSS rescore
- 2026-10-08 18:36 UTCEG score recompute
- 2026-10-08 17:59 UTCEG score recompute
- 2026-10-08 17:25 UTCEG score recompute
- 2026-10-08 17:15 UTCEG score recompute
- 2026-10-08 17:14 UTCMITRE cvelistV5first tracked
Related CVEs(same product + same CWE)
Same product
10 shownPyPI:pydantic-ai
Frequently asked(5)
What is CVE-2026-107295?
When was CVE-2026-107295 disclosed?
Is CVE-2026-107295 actively exploited?
What is the CVSS score of CVE-2026-107295?
How do I remediate CVE-2026-107295?
Dependency Blast Radius
See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-107295
Is Your Infrastructure Affected by CVE-2026-107295?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.