Skip to content
Noroxi
CVE.org (no NVD analysis yet)· CNA GitHub_M

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

HighCVSS 7.6 · v3.1—No exploit Fix available

Noroxi assessment

Priority: Monitor (action score 30/100)

  • The sources we track (CISA KEV, Exploit-DB, Metasploit, Nuclei, GitHub) show no public exploit code or exploitation in the wild.
  • Probability of exploitation in the next 30 days: 0.15% (FIRST EPSS).
  • Anyone who can reach it over the internet can trigger it. No account or password is required. A user must open a link or visit a page. No special conditions are required; it is repeatable.
  • Fixed version: pydantic-ai (PyPI) 1.107.4, 2.28.0; pydantic-ai-slim (PyPI) 1.107.4, 2.28.0.

Low priority for now. Upgrade to pydantic-ai (PyPI) 1.107.4, 2.28.0; pydantic-ai-slim (PyPI) 1.107.4, 2.28.0 or later.

Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it

Primary sources: NVD · CVE.org · FIRST EPSS

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.

Published
Oct 8, 2026
Updated
Oct 13, 2026
EPSS
0.1% · 5th percentile

Report tools

JSON

Action score

30

Monitor

Low priority for now.

CVSS
30 / 40 · 7.6 / 10
CISA KEV
0 / 30 · Not listed
EPSS
0 / 30 · 0.1%

CISA SSVC decision

Exploitation
none
Automatable
no
Technical impact
partial

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD
—
CNA · GitHub_M
7.6
NVD has not scored this yet; the score shown is the CNA’s.

The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.

Get told when this record changes

  • Not in KEV: no record of exploitation in the wild
  • No public exploit code on record
  • A fix has been released

If any of these changes, we'll tell you in the daily email digest.

Follow CVE-2026-107295

When you'll hear from us

  • when it enters CISA KEV
  • when exploit code appears or is weaponized
  • when the record is updated (including a fixed version)
  • when EPSS rises 20 points in a week

One daily email digest (06:00 UTC); connect a webhook for KEV listings and weaponized exploits every 10 minutes on paid plans, on the hour on the free plan.

Your free account also gets you

  • CVE alerts: add the products and versions you run, get the new CVEs that affect them
  • Uptime monitoring: 1 site, instant email when it goes down
  • Add your domain: subdomains and takeover risk scanned every week (1 domain)
  • 10 scans an hour on the security tools, at most 30 a day (3 a day without an account), an API key and MCP
  • All your scans in one panel: findings, what changed in the last scan, a report per domain or per client (PDF, share link)
All free tools

Sign up with email · Have an account? Sign in

Free account, no card. Unfollow any time.

Don't want an account? Get "Exploited this week" by email every MondayDon't want an account? RSS feed for pydantic records
Is your version affected? Check it

Noroxi analysis

What does it mean in your environment?

The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.

We use this product, ask for help

Affected systems

Is your version affected?

Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.

VendorProduct
pydanticpydantic ai

Versions reported by the vendor

Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.

  • pydantic pydantic-ai

    • >= 1.34.0, < 1.107.4, >= 2.0.0b1, < 2.28.0affected

  • pydantic pydantic-ai-slim

    • >= 1.34.0, < 1.107.4, >= 2.0.0b1, < 2.28.0affected

Affected versions

NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.

  • pydantic pydantic ai1.34.0 and later · before 1.107.4
  • pydantic pydantic ai2.0.0 and later · before 2.28.0

Package-level exposure

OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.

EcosystemPackageAffected rangeFix
PyPIpydantic-aifrom 1.34.0 · before 1.107.41.107.4
PyPIpydantic-aifrom 2.0.0b1 · before 2.28.02.28.0
PyPIpydantic-ai-slimfrom 1.34.0 · before 1.107.41.107.4
PyPIpydantic-ai-slimfrom 2.0.0b1 · before 2.28.02.28.0

Same product

pydantic: all records

Other highest-scoring records for the same primary product.

  • CVE-2026-25580Pydantic AI Affected by Server-Side Request Forgery (SSRF) in URL Download Handling
    34Monitor
  • CVE-2026-107286Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends early
    30Monitor
  • CVE-2026-107289Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv6 zone identifier (incomplete fix for CVE-2026-46678 and CVE-2026-48782)
    27Monitor

Published before and after this one in the same product

  • ← EarlierCVE-2026-107292Oct 8, 2026 · Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the local chat endpoint does not validate the `Host` header
    25Monitor
  • ← EarlierCVE-2026-107293Oct 8, 2026 · Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`
    9Monitor
  • ← EarlierCVE-2026-107294Oct 8, 2026 · Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl
    26Monitor

Remediation

Which version to upgrade to

Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.

Product / packageFixed versionSource
PyPI:pydantic-ai1.107.4Package registry (OSV)
PyPI:pydantic-ai2.28.0Package registry (OSV)
PyPI:pydantic-ai-slim1.107.4Package registry (OSV)
PyPI:pydantic-ai-slim2.28.0Package registry (OSV)

Exploit status

No known public exploit

No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.

Research context

For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.

Timeline

From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.

  1. Published
  2. Fix recordedsame day
  3. TodayNov 13, 2026+36 d
EPSS, last 120 days

FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).

Patch and commit links

Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.

Not on record for this CVE: researcher credit · variant or chain candidate · public bounty program.

Technical details

Attack conditions

  • Anyone who can reach it over the internet can trigger it.
  • No account or password is required.
  • A user must open a link or visit a page.
  • No special conditions are required; it is repeatable.

If successful

Confidentiality
low · data can be read
Integrity
high · data or configuration can be modified
Availability
low · the service can be disrupted
Attack vector
Network
Attack complexity
Low
Privileges required
None
User interaction
Required
Scope
Unchanged
Confidentiality impact
Low
Integrity impact
High
Availability impact
Low

Weakness class (CWE)

CWE-352 · Cross-Site Request Forgery (CSRF)

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L

nvd-secondary

Root cause

State-changing requests rely on the session cookie the browser sends automatically; nothing verifies that the request came from the user’s own page.

The bug in code

The whole CWE-352 class

A representative example of this vulnerability class. Not the vendor's source code; it shows the faulty pattern and its fix.

Vulnerable

ts
app.use(session({ cookie: { httpOnly: true } }));app.post("/account/address", updateAddress);

Fixed

ts
app.use(session({ cookie: { httpOnly: true, sameSite: "lax" } }));app.post("/account/address", csrfProtection, updateAddress);

Attack context

MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.

ATT&CK techniques

—

References

Show all references (6 more)

Vendor advisories and official records. Exploit/PoC links are deliberately left out.

All records