CVE-2026-107293
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.
Does this matter?
Lower severity and a low EPSS score (0.30%). Track it; it rarely justifies an emergency change on its own.
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.
- CVSS 4.0
- 2.3 LOWCVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/M
- EPSS
- 0.30% probability · 22th percentile
- Public exploits
- None in Exploit-DB
- CISA KEV
- Not listed
- Weakness
- CWE-212, CWE-532
- Affected
- pydantic/pydantic ai
- Source
- security-advisories@github.com
EPSS moved from 0.3% on 9 October 2026 to 0.3% on 26 October 2026.
References
- https://github.com/pydantic/pydantic-ai/commit/fe9dbed7b7ccf7e7128b5786886e4441f6f5594fPatch
- https://github.com/pydantic/pydantic-ai/pull/7357Patch, Vendor Advisory
- https://github.com/pydantic/pydantic-ai/releases/tag/v2.27.1Patch, Release Notes, Vendor Advisory
- https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-3gh4-cghq-f8v4Mitigation, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.