Vulnerability-Lookup

GHSA-2JRP-274C-JHV3

Vulnerability from github – Published: 2026-02-06 18:32 – Updated: 2026-02-06 21:42

Summary

Pydantic AI has Server-Side Request Forgery (SSRF) in URL Download Handling

Details

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:

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)
Steal cloud credentials: Access cloud metadata endpoints (AWS IMDSv1 at 169.254.169.254, GCP, Azure, Alibaba Cloud)
Scan internal networks: Enumerate internal hosts and ports

Who Is Affected

You are affected if your application:

Uses Agent.to_web or clai web - The web interface accepts file attachments via the Vercel AI Data Stream Protocol, where users can provide arbitrary URLs through chat messages.
Uses VercelAIAdapter - Chat interfaces built with Vercel AI SDK allow users to submit messages containing URLs that are processed server-side.
Uses AGUIAdapter or Agent.to_ag_ui - The AG-UI protocol allows users to provide file references with URLs as part of agent interactions.
Exposes a custom API accepting message history - Any endpoint that accepts message history or ImageUrl, AudioUrl, VideoUrl, DocumentUrl objects from user input.

Attack Scenario

Via chat interface, an attacker submits a message with a file attachment pointing to an internal resource:

{
  "role": "user",
  "parts": [
    {"type": "file", "mediaType": "image/png", "url": "http://169.254.169.254/latest/meta-data/iam/security-credentials/"}
  ]
}

Affected Model Integrations

Multiple model integrations download URL content in certain conditions:

Provider	Downloaded Types
`OpenAIChatModel`	`AudioUrl`, `DocumentUrl`
`AnthropicModel`	`DocumentUrl` (`text/plain`)
`GoogleModel` (GLA)	All URL types (except YouTube and Files API URLs)
`XaiModel`	`DocumentUrl`
`BedrockConverseModel`	`ImageUrl`, `DocumentUrl`, `VideoUrl` (non-S3 URLs)
`OpenRouterModel`	`AudioUrl`

Remediation

Upgrade to Patched Version

Upgrade to the patched version or later. The fix adds comprehensive SSRF protection:

Blocks private/internal IP addresses by default
Always blocks cloud metadata endpoints (even with allow-local)
Only allows http:// and https:// protocols
Resolves hostnames before requests to prevent DNS rebinding
Validates each redirect target

New `force_download='allow-local'` Option

If an application legitimately needs to access local/private network resources (e.g., in a fully trusted internal environment), it can explicitly opt in:

from pydantic_ai import ImageUrl

# Default behavior: private IPs are blocked
ImageUrl(url="http://internal-service/image.png")  # Raises ValueError

# Opt-in to allow local access (use with caution)
ImageUrl(url="http://internal-service/image.png", force_download='allow-local')

Important: Cloud metadata endpoints (169.254.169.254, fd00:ec2::254, 100.100.100.200) are always blocked, even with allow-local.

Workaround for Older Versions

If a project cannot upgrade immediately, use a history processor to filter out URLs targeting local/private addresses:

import ipaddress
import socket
from urllib.parse import urlparse

from pydantic_ai import Agent, ModelMessage, ModelRequest
from pydantic_ai.messages import AudioUrl, DocumentUrl, ImageUrl, VideoUrl

def is_private_url(url: str) -> bool:
    """Check if a URL targets a private/internal IP address."""
    try:
        parsed = urlparse(url)
        hostname = parsed.hostname
        if not hostname:
            return True  # Invalid URL, block it

        # Resolve hostname to IP
        ip_str = socket.gethostbyname(hostname)
        ip = ipaddress.ip_address(ip_str)

        # Block private, loopback, and link-local addresses
        return ip.is_private or ip.is_loopback or ip.is_link_local
    except (socket.gaierror, ValueError):
        return True  # DNS resolution failed, block it

def filter_private_urls(messages: list[ModelMessage]) -> list[ModelMessage]:
    """Remove URL parts that target private/internal addresses."""
    url_types = (ImageUrl, AudioUrl, VideoUrl, DocumentUrl)
    filtered = []
    for msg in messages:
        if isinstance(msg, ModelRequest):
            safe_parts = [
                part for part in msg.parts
                if not (isinstance(part, url_types) and is_private_url(part.url))
            ]
            if safe_parts:
                filtered.append(ModelRequest(parts=safe_parts))
        else:
            filtered.append(msg)
    return filtered

# Apply the filter to your agent
agent = Agent('openai:gpt-5', history_processors=[filter_private_urls])

Technical Details of the Fix

The fix introduces a new _ssrf.py module with comprehensive protection:

Protocol validation: Only http:// and https:// allowed
DNS resolution before request: Prevents DNS rebinding attacks
Private IP blocking (by default):
127.0.0.0/8, ::1/128 (loopback)
10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16 (private)
169.254.0.0/16, fe80::/10 (link-local)
100.64.0.0/10 (CGNAT)
fc00::/7 (unique local)
2002::/16 (6to4, can embed private IPv4)
Cloud metadata always blocked: 169.254.169.254, fd00:ec2::254, 100.100.100.200
Safe redirect handling: Each redirect validated before following (max 10)

Severity ?

8.6 (High)


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

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "pydantic-ai"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.0.26"
            },
            {
              "fixed": "1.56.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "pydantic-ai-slim"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.0.26"
            },
            {
              "fixed": "1.56.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-25580"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-02-06T18:32:39Z",
    "nvd_published_at": "2026-02-06T21:16:17Z",
    "severity": "HIGH"
  },
  "details": "## Summary\n\nA Server-Side Request Forgery (SSRF) vulnerability exists in Pydantic AI\u0027s 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.\n\n**This vulnerability only affects applications that accept message history from external users**, such as those using:\n- **`Agent.to_web`** or **`clai web`** to serve a chat interface\n- **`VercelAIAdapter`** for Vercel AI SDK integration\n- **`AGUIAdapter`** or **`Agent.to_ag_ui`** for AG-UI protocol integration\n- Custom APIs that accept message history from user input\n\nApplications that only use hardcoded or developer-controlled URLs are not affected.\n\n### Description\n\nThe `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:\n\n1. **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`)\n2. **Steal cloud credentials**: Access cloud metadata endpoints (AWS IMDSv1 at `169.254.169.254`, GCP, Azure, Alibaba Cloud)\n3. **Scan internal networks**: Enumerate internal hosts and ports\n\n### Who Is Affected\n\nYou are affected if your application:\n\n1. **Uses `Agent.to_web` or `clai web`** - The web interface accepts file attachments via the Vercel AI Data Stream Protocol, where users can provide arbitrary URLs through chat messages.\n\n2. **Uses `VercelAIAdapter`** - Chat interfaces built with Vercel AI SDK allow users to submit messages containing URLs that are processed server-side.\n\n3. **Uses `AGUIAdapter` or `Agent.to_ag_ui`** - The AG-UI protocol allows users to provide file references with URLs as part of agent interactions.\n\n4. **Exposes a custom API accepting message history** - Any endpoint that accepts message history or `ImageUrl`, `AudioUrl`, `VideoUrl`, `DocumentUrl` objects from user input.\n\n### Attack Scenario\n\nVia chat interface, an attacker submits a message with a file attachment pointing to an internal resource:\n```json\n{\n  \"role\": \"user\",\n  \"parts\": [\n    {\"type\": \"file\", \"mediaType\": \"image/png\", \"url\": \"http://169.254.169.254/latest/meta-data/iam/security-credentials/\"}\n  ]\n}\n```\n\n### Affected Model Integrations\n\nMultiple model integrations download URL content in certain conditions:\n\n| Provider | Downloaded Types |\n|----------|------------------|\n| `OpenAIChatModel` | `AudioUrl`, `DocumentUrl` |\n| `AnthropicModel` | `DocumentUrl` (`text/plain`) |\n| `GoogleModel` (GLA) | All URL types (except YouTube and Files API URLs) |\n| `XaiModel` | `DocumentUrl` |\n| `BedrockConverseModel` | `ImageUrl`, `DocumentUrl`, `VideoUrl` (non-S3 URLs) |\n| `OpenRouterModel` | `AudioUrl` |\n\n## Remediation\n\n### Upgrade to Patched Version\n\n**Upgrade** to the patched version or later. The fix adds comprehensive SSRF protection:\n\n- Blocks private/internal IP addresses by default\n- Always blocks cloud metadata endpoints (even with `allow-local`)\n- Only allows `http://` and `https://` protocols\n- Resolves hostnames before requests to prevent DNS rebinding\n- Validates each redirect target\n\n### New `force_download=\u0027allow-local\u0027` Option\n\nIf an application legitimately needs to access local/private network resources (e.g., in a fully trusted internal environment), it can explicitly opt in:\n\n```python\nfrom pydantic_ai import ImageUrl\n\n# Default behavior: private IPs are blocked\nImageUrl(url=\"http://internal-service/image.png\")  # Raises ValueError\n\n# Opt-in to allow local access (use with caution)\nImageUrl(url=\"http://internal-service/image.png\", force_download=\u0027allow-local\u0027)\n```\n\n**Important**: Cloud metadata endpoints (`169.254.169.254`, `fd00:ec2::254`, `100.100.100.200`) are **always blocked**, even with `allow-local`.\n\n### Workaround for Older Versions\n\nIf a project cannot upgrade immediately, use a [history processor](https://ai.pydantic.dev/message-history/#processing-message-history) to filter out URLs targeting local/private addresses:\n\n```python\nimport ipaddress\nimport socket\nfrom urllib.parse import urlparse\n\nfrom pydantic_ai import Agent, ModelMessage, ModelRequest\nfrom pydantic_ai.messages import AudioUrl, DocumentUrl, ImageUrl, VideoUrl\n\ndef is_private_url(url: str) -\u003e bool:\n    \"\"\"Check if a URL targets a private/internal IP address.\"\"\"\n    try:\n        parsed = urlparse(url)\n        hostname = parsed.hostname\n        if not hostname:\n            return True  # Invalid URL, block it\n\n        # Resolve hostname to IP\n        ip_str = socket.gethostbyname(hostname)\n        ip = ipaddress.ip_address(ip_str)\n\n        # Block private, loopback, and link-local addresses\n        return ip.is_private or ip.is_loopback or ip.is_link_local\n    except (socket.gaierror, ValueError):\n        return True  # DNS resolution failed, block it\n\ndef filter_private_urls(messages: list[ModelMessage]) -\u003e list[ModelMessage]:\n    \"\"\"Remove URL parts that target private/internal addresses.\"\"\"\n    url_types = (ImageUrl, AudioUrl, VideoUrl, DocumentUrl)\n    filtered = []\n    for msg in messages:\n        if isinstance(msg, ModelRequest):\n            safe_parts = [\n                part for part in msg.parts\n                if not (isinstance(part, url_types) and is_private_url(part.url))\n            ]\n            if safe_parts:\n                filtered.append(ModelRequest(parts=safe_parts))\n        else:\n            filtered.append(msg)\n    return filtered\n\n# Apply the filter to your agent\nagent = Agent(\u0027openai:gpt-5\u0027, history_processors=[filter_private_urls])\n```\n\n## Technical Details of the Fix\n\nThe fix introduces a new `_ssrf.py` module with comprehensive protection:\n\n1. **Protocol validation**: Only `http://` and `https://` allowed\n2. **DNS resolution before request**: Prevents DNS rebinding attacks\n3. **Private IP blocking** (by default):\n   - `127.0.0.0/8`, `::1/128` (loopback)\n   - `10.0.0.0/8`, `172.16.0.0/12`, `192.168.0.0/16` (private)\n   - `169.254.0.0/16`, `fe80::/10` (link-local)\n   - `100.64.0.0/10` (CGNAT)\n   - `fc00::/7` (unique local)\n   - `2002::/16` (6to4, can embed private IPv4)\n4. **Cloud metadata always blocked**: `169.254.169.254`, `fd00:ec2::254`, `100.100.100.200`\n5. **Safe redirect handling**: Each redirect validated before following (max 10)",
  "id": "GHSA-2jrp-274c-jhv3",
  "modified": "2026-02-06T21:42:27Z",
  "published": "2026-02-06T18:32:39Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-2jrp-274c-jhv3"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-25580"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/commit/d398bc9d39aecca6530fa7486a410d5cce936301"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/pydantic/pydantic-ai"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Pydantic AI has Server-Side Request Forgery (SSRF) in URL Download Handling"
}

CVE-2026-25580 (GCVE-0-2026-25580)

Vulnerability from cvelistv5 – Published: 2026-02-06 21:01 – Updated: 2026-02-06 21:01

Title

Pydantic AI Affected by Server-Side Request Forgery (SSRF) in URL Download Handling

Summary

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.0.26 to before 1.56.0, aServer-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. This vulnerability is fixed in 1.56.0.

Severity ?

8.6 (High)


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

CWE

CWE-918 - Server-Side Request Forgery (SSRF)

Assigner

GitHub_M

References

URL

	Vendor	Product	Version
	pydantic	pydantic-ai	Affected: >= 0.0.26, < 1.56.0

Sightings

Author	Source	Type	Date

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

Detection rules are retrieved from Rulezet.

Action not permitted

GHSA-2JRP-274C-JHV3

Summary

Description

Who Is Affected

Attack Scenario

Affected Model Integrations

Remediation

Upgrade to Patched Version

New force_download='allow-local' Option

Workaround for Older Versions

Technical Details of the Fix

CVE-2026-25580 (GCVE-0-2026-25580)

Tags

Sightings

Nomenclature

New `force_download='allow-local'` Option