UTC

pydantic-ai-slim

14 published advisories; version 2.53.0 or later fixes all of them.

Registry
PyPI
Advisories
14
Latest fix
2.53.0
Exploited in the wild
None listed

Check your machine

Finds pydantic-ai-slim in your agent and MCP configs, installed skills, global npm packages, the npx and uvx caches, uv and pipx tools, Claude Code and Cursor. It runs offline and sends nothing anywhere.

pip install "shieldpi>=0.10.0"
shieldpi agent-config . --installed
Provenance

Source: github.com/pydantic/pydantic-ai, named in the package metadata (not verified)

10 of the last 10 releases of pydantic-ai-slim were published with build provenance: a signed record of the repository and commit each was built from, which the registry checks before it accepts the release.

  • 2.70.0
  • 2.69.0
  • 2.68.0
  • 2.67.0
  • 1.107.10
  • 2.66.0
  • 2.65.0
  • 2.64.0
  • 2.63.0
  • 2.62.0

Green: published with provenance. Grey: without.

OpenSSF Scorecard has not scored this repository.

Provenance from deps.dev (CC BY 4.0); Scorecard from OpenSSF (CDLA-Permissive-2.0). As of 2026-11-18.

Advisories
AdvisorySeverityAffectedFixed inPublished
Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`CVE-2026-107293Low>= 0.3.4, < 1.107.41.107.42026-10-08
Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`CVE-2026-107293Low>= 2.0.0b1, < 2.27.12.27.12026-10-08
Pydantic AI OpenTelemetry instrumentation: exception events on tool and agent run spans include content when `include_content=False`CVE-2026-107291Low>= 0.3.4, < 1.107.61.107.62026-10-08
Pydantic AI OpenTelemetry instrumentation: exception events on tool and agent run spans include content when `include_content=False`CVE-2026-107291Low>= 2.0.0b1, < 2.44.02.44.02026-10-08
Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends earlyCVE-2026-107286High>= 2.10.0, < 2.53.02.53.02026-10-08
Pydantic AI: Event loop blocked by quadratic title extraction in `web_fetch`CVE-2026-107290Medium>= 1.77.0, < 1.107.61.107.62026-10-08
Pydantic AI: Event loop blocked by quadratic title extraction in `web_fetch`CVE-2026-107290Medium>= 2.0.0b1, < 2.44.02.44.02026-10-08
Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execuCVE-2026-107295High>= 1.34.0, < 1.107.41.107.42026-10-08
Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execuCVE-2026-107295High>= 2.0.0b1, < 2.28.02.28.02026-10-08
Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the local chat endpoint does not validate the `Host` headerCVE-2026-107292Medium>= 1.34.0, < 1.107.51.107.52026-10-08
Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the local chat endpoint does not validate the `Host` headerCVE-2026-107292Medium>= 2.0.0b1, < 2.30.02.30.02026-10-08
Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrlCVE-2026-107294Medium>= 1.77.0, < 1.107.21.107.22026-10-08
Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrlCVE-2026-107294Medium>= 2.0.0b1, <= 2.23.02.24.02026-10-08
Pydantic AI: Excessive resource use when local web fetching converts nested HTMLCVE-2026-107287Medium>= 1.77.0, < 1.107.71.107.72026-10-08
Pydantic AI: Excessive resource use when local web fetching converts nested HTMLCVE-2026-107287Medium>= 2.0.0b1, < 2.52.02.52.02026-10-08
Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv6 zone identifiersCVE-2026-107289Medium>= 1.56.0, < 1.107.61.107.62026-10-08
Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv6 zone identifiersCVE-2026-107289Medium>= 2.0.0b1, < 2.44.02.44.02026-10-08
Pydantic AI: Unvalidated UploadedFile references in UI adapters allow server-side file access using the application's credentialsCVE-2026-54249Medium>= 1.65.0, < 1.106.01.106.02026-08-13
Pydantic AI: Unvalidated UploadedFile references in UI adapters allow server-side file access using the application's credentialsCVE-2026-54249Medium>= 2.0.0b1, < 2.0.0b62.0.0b62026-08-13
pydantic-ai: SSRF blocklist bypass via IPv4-compatible, SIIT/IVI, and local NAT64 IPv6 addresses (incomplete fix of CVE-2026-46678)CVE-2026-48782Medium>= 1.56.0, < 1.102.01.102.02026-06-26
pydantic-ai: SSRF blocklist bypass via IPv4-compatible, SIIT/IVI, and local NAT64 IPv6 addresses (incomplete fix of CVE-2026-46678)CVE-2026-48782Medium>= 2.0.0b1, < 2.0.0b32.0.0b32026-06-26
Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv4-mapped IPv6 (Incomplete fix of CVE-2026-25580)CVE-2026-46678Medium>= 1.56.0, < 1.99.01.99.02026-05-21
Pydantic AI has Server-Side Request Forgery (SSRF) in URL Download HandlingCVE-2026-25580High>= 0.0.26, < 1.56.01.56.02026-02-06
Pydantic AI has Stored XSS via Path Traversal in Web UI CDN URLCVE-2026-25640High>= 1.34.0, < 1.51.01.51.02026-02-06

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].