CVE-2026-107293 Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`
Attackers with telemetry access can read sensitive validation feedback and model values from retry prompts when content redaction is enabled.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-107293?
CVE-2026-107293 is a low-severity vulnerability in pydantic-ai, published on 8 Oct 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.3.4 until 1.107.4 and 2.27.1, OpenTelemetry instrumentation configured with InstrumentationSettings(include_content=False) can export retry prompts outside tool calls in gen_ai.input.messages and pydantic_ai.all_messages. Agents using NativeOutput, PromptedOutput, or output validators on text output can therefore disclose validation feedback, including invalid model values quoted by that feedback, to readers of the telemetry backend. Tool-call retries and deployments that do not use include_content=False are not affected by this specific path. This issue is fixed in versions 1.107.4 and 2.27.1.
Which versions are affected by CVE-2026-107293?
10 open source packages ship an affected version, including pydantic-ai and pydantic-ai-slim. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
pydantic-ai PyPI | From 0.3.4 | 1.107.4, 2.27.1 |
pydantic-ai PyPI | From 0.3.4 | 1.107.4 |
pydantic-ai PyPI | From 0.3.4 | 1.107.4 |
pydantic-ai PyPI | From 2.0.0b1 | 2.27.1 |
pydantic-ai PyPI | From 2.0.0b1 | 2.27.1 |
pydantic-ai-slim PyPI | From 0.3.4 | 1.107.4, 2.27.1 |
4 more packages
pydantic-ai-slim PyPI | From 0.3.4 | 1.107.4 |
pydantic-ai-slim PyPI | From 0.3.4 | 1.107.4 |
pydantic-ai-slim PyPI | From 2.0.0b1 | 2.27.1 |
pydantic-ai-slim PyPI | From 2.0.0b1 | 2.27.1 |
Products include Pydantic Pydantic Ai.
How do I fix CVE-2026-107293?
Upgrade pydantic-ai to a fixed version for your release line: 1.107.4 or 2.27.1.
Is CVE-2026-107293 being exploited?
There is no known exploitation of CVE-2026-107293 in the wild and no public exploit code.
Other vulnerabilities in pydantic-ai
- CVE-2026-25580 Pydantic AI Affected by Server-Side Request Forgery (SSRF) in URL Download Handling
- CVE-2026-107295 Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint
- CVE-2026-107286 Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends early
- CVE-2026-25640 Pydantic AI affected by Stored XSS via Path Traversal in Web UI CDN URL
- CVE-2026-107289 Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv6 zone identifiers
Sources
Also known as CLEANSTART-2026-XD01399, GHSA-3gh4-cghq-f8v4, PYSEC-2026-4274, PYSEC-2026-4283.