pydantic-ai-slim

How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.

Version: 1.71.0 registry icon
Safety score
20
Check your open source dependency risks. Get immediate insight about security, stability and licensing risks.
Security Risks of Known Vulnerabilities
CVE-2026-107293
CWE-212
Threat level: LOW | CVSS score: 2

Pydantic AI's OpenTelemetry instrumentation supports InstrumentationSettings(include_content=False) to exclude message content — user prompts, model completions, tool call arguments and responses — from exported telemetry, so that agents can be monitored without sending sensitive content to the observability backend.



CVE-2026-107289
CWE-918
Threat level: MEDIUM | CVSS score: 5

When an application using Pydantic AI opts a URL into local network access — either a FileUrl with force_download='allow-local', or web_fetch_tool(allow_local_urls=True) — the cloud-metadata blocklist could be bypassed by appending an IPv6 zone identifier to a metadata address (for example fd00:ec2::254%251). The host ignores the zone identifier on a destination that is not link-local and delivers the request to the metadata endpoint anyway, exposing cloud IAM short-term credentials.



CVE-2026-107295
CWE-346
Threat level: HIGH | CVSS score: 8

The Pydantic AI development web chat UI (Agent.to_web(), clai web) did not check the content type of requests to its chat endpoint. This allowed a website visited by a developer to submit a request to a chat UI running on that developer's machine, causing the served agent to run and to execute its tools with the privileges and credentials of the local process.



CVE-2026-107291
CWE-212
Threat level: LOW | CVSS score: 2

Pydantic AI's OpenTelemetry instrumentation supports InstrumentationSettings(include_content=False) to exclude message content — user prompts, model completions, tool call arguments and responses, and any other message content — from exported telemetry, so that agents can be monitored without sending sensitive content to the observability backend.



CVE-2026-107292
CWE-346
Threat level: MEDIUM | CVSS score: 5

The Pydantic AI development web chat UI (Agent.to_web(), clai web) does not validate the Host header of incoming requests. A website a developer visits can use DNS rebinding to make requests to a chat UI running on that developer's machine appear same-origin to the browser, causing the served agent to run and to execute its tools with the privileges and credentials of the local process.



Please note that this component is affected by 3 other vulnerabilities
0 Critical  |  0 High  |  3 Medium  |  0 Low  |  0 Suggest

Latest safe minor: 1.107.7 - Latest safe major: 2.55.0 Scan your application codebase with Meterian to see all known vulnerabilities in your open source software dependencies.


Stability

Stay updated with the latest patches and releases. Plan your sofware desisgn. Avoid common known vulnerabilities fixed by the open source community

Latest patch release:   --

Latest minor release:   1.107.7

Latest major release:   2.55.0

Licensing

Maintain your licence declarations and avoid unwanted licences to protect your IP the way you intended.

MIT   -   MIT License

Not a wildcard

Not proprietary

OSI Compliant