Sign in Sign up
JA · EN · FR
SecPulse
Categories
CVE-2026-25580 high CVSS 8.6

SSRF (Server-Side Request Forgery) in pydantic-ai (CVE-2026-25580)

Summary

SSRF in pydantic-ai (CVE-2026-25580). Confidential information can be exposed externally. Exploitable via Agent.to_web. Mitigation: upgrade to 1.56.0 or later.

Original description

The description as published by the source.

Summary

A Server-Side Request Forgery (SSRF) vulnerability exists in Pydantic AI's URL download functionality. When applications accept message history from untrusted sources, attackers can include malicious URLs that cause the server to make HTTP requests to internal network resources, potentially accessing internal services or cloud credentials.

This vulnerability only affects applications that accept message history from external users, such as those using:

  • Agent.to_web or clai web to serve a chat interface
  • VercelAIAdapter for Vercel AI SDK integration
  • AGUIAdapter or Agent.to_ag_ui for AG-UI protocol integration
  • Custom APIs that accept message history from user input

Applications that only use hardcoded or developer-controlled URLs are not affected.

Description

The download_item() helper function downloads content from URLs without validating that the target is a public internet address. When user-supplied message history contains URLs, attackers can:

  1. Access internal services: Request http://127.0.0.1, localhost, or private IP ranges (10.x.x.x, 172.16.x.x, 192.168.x.x)
  2. Steal cloud credentials: Access cloud metadata endpoints (AWS IMDSv1 at 169.254.169.254, GCP, Azure, Alibaba Cloud)
  3. Scan internal networks: Enumerate internal hosts and ports

Who Is Affected

You are affected if your application:

  1. Uses Agent.to_web or clai web - The web interface accepts file attachments…

Source: NIST National Vulnerability Database NVD GitHub Advisory

Auto-generated summary

Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.

A vulnerability tracked as CVE-2026-25580 has been found in pydantic-ai.
Attackers can target a specific entry point like Agent.to_web over the network to misuse the product.
Confidential information can be exposed externally. CVSS score: 8.6/10.
What to do: upgrade pydantic-ai to 1.56.0 or later.
If unsure, ask your IT team or search "pydantic-ai CVE-2026-25580" on the vendor's site.

CVE-2026-25580 (pydantic-ai) — CWE-918 / CVSS v3 8.6
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Attack surface: Agent.to_web / VercelAIAdapter / AGUIAdapter / Agent.to_ag_ui
Patched: 1.56.0 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.

❓ What is the problem

SSRF (CWE-918) exists in pydantic-ai. Attackers reach the vulnerable code path via Agent.to_web without authentication.

📍 Affected scope

Check the vendor advisory for the affected versions of pydantic-ai. Attack surface: Agent.to_web / VercelAIAdapter / AGUIAdapter / Agent.to_ag_ui.

🔥 Severity

Severity: High (CVSS 8.6/10). Confidential information can be exposed externally.

🔧 How to fix

Update to 1.56.0.

🛡️ Workaround

Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.

🔍 Detection

Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'pydantic-ai' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.

Response actions

Concrete steps and command examples for SOC/SRE teams to execute in order

  1. 1
    Identify exposure identify 
    grep -r 'pydantic-ai' . | grep -v node_modules

    リポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で pydantic-ai を grep し、稼働しているサービス・バージョンを把握する。

  2. 2
    Apply patch patch 
    Upgrade pydantic-ai to 1.56.0

    ステージング環境で 1.56.0 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスを含めること。

  3. 3
    Post-deployment verification verify 
    Confirm patched version is live in production

    パッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。

Affected packages

PyPI pydantic-ai
[{"type":"ECOSYSTEM","events":[{"introduced":"0.0.26"},{"fixed":"1.56.0"}]}]
PyPI pydantic-ai-slim
[{"type":"ECOSYSTEM","events":[{"introduced":"0.0.26"},{"fixed":"1.56.0"}]}]

References

We use cookies for analytics and ad measurement. This setting applies to all Game co., Ltd. sites. Details