HOL LogoGuard

Explore HOL

  • HOL home
  • AI agent registry
  • AI plugins
  • Open standards
  • HOL members
  • Sponsor HOL
  • Advertise with HOL

Guard product

  • Guard overviewLocal security and control for AI agents and the tools they use.
  • FeaturesRuntime protection, policy routing, review, and evidence.

Explore Guard

  • Product previewWalk through Guard surfaces in read-only demo mode.
  • ComparisonCompare Guard with native controls and AI security vendors.

AI tools

  • All AI toolsEvery supported AI tool and how Guard applies policy to it.
  • Codex
  • Claude Code
  • Cursor
  • Antigravity CLI
  • OpenCode
  • Hermes
  • OpenClaw
  • GitHub Copilot CLI
  • Antigravity
  • Kimi
  • Grok
  • Pi / Oh My Pi
  • Zcode

Extensions

  • All extensionsBrowse command and MCP coverage with owners and stated limits.
  • Command coverageShell command protection across clouds, databases, backups, and packages.
  • MCP server coverageSee how Guard maps risk state across MCP tools and servers.
  • Core safetyThe safety floor listings that ship with Guard.
  • Data and resilienceBackup and storage command protection.
  • Cloud and infrastructureAWS, Azure, GCP, Kubernetes, and more.

Security

  • AI security hubSecurity research, advisories, and agent safety coverage.
  • AI tool securitySecurity profiles for each supported coding agent.
  • Safe labsHands-on attack simulations with safe boundaries.
  • Redacted warningsReal blocked actions with sensitive details removed.
  • AdvisoriesCoordinated disclosure reports for AI tooling.
  • Active CVEsSearch active CVEs affecting AI tooling.

Learn

  • Security guidesPractical guides for securing AI agent workflows.
  • DocsInstall, configure, and operate Guard with confidence.
  • ResearchPublished security research, benchmarks, and methodology.

Community

  • ReleasesVersion history, shipped changes and upgrade notes.
  • ContributorsThe people and contributions behind HOL Guard.
  • AffiliatesShare Guard with your audience and earn from referrals.
  • SponsorFund agreed research, implementation and shared testing through the HOL Partner Program.
  • AdvertiseCompare README logo placements, previews and monthly prices, or promote a plugin or extension.
PricingEnterpriseOpen AppInstall Guard
  1. Guard
  2. Security
  3. CVEs
  4. CVE 2026 46678 pydantic ai ssrf cloud metadata blocklist bypass
HOL Guard

Public security guidance for teams protecting AI harnesses, MCP servers, skills, prompts, and local tool execution.

Install Guard

AI Security

  • Prompt injection
  • MCP security
  • OWASP MCP mapping
  • Supply chain

Resources

  • Trust packet
  • Harness setup
  • Redacted warnings
  • Safe labs

Product

  • Install Guard
  • Pricing
  • Open dashboard
Guard
  • Guard Overview
  • Releases
  • Contributors
  • Install Guard
  • Pricing
Docs
  • Documentation Index
  • Developer Hub
  • API Reference
  • Root OpenAPI
  • Registry OpenAPI
  • Run in Postman
  • Standards
  • Submit ERC-8004 Contract
  • Feature Your Agent
Best Plugins
  • Browse Plugins
  • Plugin Launches
  • Best Claude Plugins
  • Best Codex Plugins
  • Best Grok Plugins
  • Best Kimi Plugins
  • Best DeepSeek Plugins
  • Best Antigravity Plugins
  • Best MCP Servers
  • Best Cursor Plugins
  • Best OpenCode Plugins
Best Agents
  • Best ERC-8004 Agents
  • Best Virtuals Agents
  • Best MCP Servers
  • Best A2A Agents
  • Best x402 Payable
  • All Categories
Community
  • Contribute to HOL
  • Telegram
  • X
More
  • About HOL
  • Sponsor
  • Advertise
  • Affiliate program
  • Contact
  • Blog
  • GitHub
  • Privacy
  • Terms of Service
Settings

Copyright © 2026 HOL DAO LLC. All rights reserved.

Back to active CVEs
Medium · CVSS 6.8CVE-2026-46678

Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv4-mapped IPv6 (Incomplete fix of CVE-2026-25580)CVE-2026-46678

Answer in brief

CVE-2026-46678 records a Medium severity (CVSS 6.8) vulnerability in Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv4-mapped IPv6 (Incomplete fix of CVE-2026-25580). The current sources do not mark it as known exploited. The current feed maps pydantic/pydantic-ai (generic), pydantic/pydantic-ai-slim (generic). Check affected ranges and fixed versions before updating.

Analysis pending evidence review

HOL Guard separates source facts from reviewed analysis. See the methodology.

Published Jul 29, 2026Updated Aug 4, 2026Source checked Nov 5, 2026First seen by HOL Aug 4, 2026Material review Aug 4, 2026
Upstream Advisory

Key facts

Risk
Medium · CVSS 6.8
Exploitation
Not marked as known exploited
Affected software
3 mapped packages or products
Fix availability
Available

Why this deserves its current priority

CVSS is 6.8. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.

Analysis status

Analysis pending evidence review

Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.

Affected scope and exposure questions

The current feed maps pydantic/pydantic-ai (generic), pydantic/pydantic-ai-slim (generic). Check affected ranges and fixed versions before updating.

Affected products and reported versions
ProductAffected versionsFixed versions
cpe:2.3:a:pydantic:pydantic_ai:*:*:*:*:*:python:*:*Not reportedNot reported
Mapped affected packages and fixed versions
PackageAffected rangeFixed version
pydantic/pydantic-aigeneric>=1.56.0 <1.99.01.99.0
pydantic/pydantic-ai-slimgeneric>=1.56.0 <1.99.01.99.0

Recommended response

  1. 1Check inventory. Check lockfiles and deployed manifests for pydantic/pydantic-ai, pydantic/pydantic-ai-slim.
  2. 2Review the reported fix. Update pydantic/pydantic-ai to 1.99.0; pydantic/pydantic-ai-slim to 1.99.0 if you use the affected versions. Test the change in a non-production environment first.

Evidence timeline and material changes

  1. Published upstream

    Jul 29, 2026

    Evidence: source:cvelist:source_dates:source-dates:record
  2. Source modified

    Aug 4, 2026

    Evidence: source:cvelist:source_dates:source-dates:record
  3. First seen by HOL

    Aug 4, 2026

Sources and claim methodology

  • GitHub security advisorygithub.com
  • GitHub security advisorygithub.com
Upstream source description

Pydantic AI is a Python agent framework for building Generative AI applications. In versions 1.56.0 through 1.98.0, when an application opts a URL into force_download='allow-local' (disabling the default block on private/internal IPs), the cloud-metadata blocklist could be bypassed by encoding the metadata IP in an IPv6 transition form (IPv4-mapped IPv6, 6to4, or NAT64), exposing cloud IAM short-term credentials on dual-stack or translated networks. This is an incomplete fix of GHSA-2jrp-274c-jhv3 / CVE-2026-25580, whose remediation did not hold for IPv6-encoded forms of the metadata IPs. An application is affected only if it explicitly opts a FileUrl (ImageUrl, AudioUrl, VideoUrl, DocumentUrl) into force_download='allow-local' on a URL influenced by untrusted input; it is not affected when using bundled integrations to ingest user input (Agent.to_web / clai web, VercelAIAdapter, AGUIAdapter / Agent.to_ag_ui), since they do not propagate force_download from external data, nor when downloading only from developer-controlled URLs. This issue has been fixed in version 1.99.0.

Quoted source text, attributed separately from HOL analysis.

Related CVEs

  • Symfony: Ip Constraint public/private Modes Accept IPv4-Mapped and IPv4-Compatible IPv6 Addresses allowing SSRF Filter BypassAlso CWE-918

Record context

Vulnerability class
SSRF
EPSS
Not reported
CWE IDs
CWE-918
Source
CVE List V5
Source checked
Nov 5, 2026
References
2 linked sources
Open source record