CVE-2026-107293
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.
- CVSS 4.0
- 2.3
CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N - CVSS 3.1
- 5.3
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N - EPSS
- 0.3% chance of exploitation in the next 30 days; higher than 22% of CVEs (scores of 2026-10-25)
- CWEs
- CWE-212, CWE-532
- Published
- Modified
- Record from
- the NVD, synced
Affected
- pydantic:pydantic_ai
Packages (OSV)
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-3gh4-cghq-f8v4 | PyPI | pydantic-ai | >=0.3.4 <1.107.4 | 1.107.4 |
| GHSA-3gh4-cghq-f8v4 | PyPI | pydantic-ai | >=2.0.0b1 <2.27.1 | 2.27.1 |
| GHSA-3gh4-cghq-f8v4 | PyPI | pydantic-ai-slim | >=0.3.4 <1.107.4 | 1.107.4 |
| GHSA-3gh4-cghq-f8v4 | PyPI | pydantic-ai-slim | >=2.0.0b1 <2.27.1 | 2.27.1 |
| PYSEC-2026-4274 | PyPI | pydantic-ai | >=0.3.4 <1.107.4 >=2.0.0b1 <2.27.1 | 1.107.4, 2.27.1 |
| PYSEC-2026-4283 | PyPI | pydantic-ai-slim | >=0.3.4 <1.107.4 >=2.0.0b1 <2.27.1 | 1.107.4, 2.27.1 |