Skip to content
Fencer Vulns
medium 5.3

CVE-2026-107293 json

Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`

published 2026-10-08 31 d ago modified 2026-10-15 24 d ago also EUVD-2026-95102 , GHSA-3gh4-cghq-f8v4 , PYSEC-2026-4274 , PYSEC-2026-4283

cvss
5.3
version 3.1, NVD
cisa kev
Not listed
not in CISA's catalog
epss
0.3%
EPSS 0.3% chance of exploitation in 30 days, percentile 22%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi pydantic-ai 1.107.4, 2.27.1
  • pypi pydantic-ai-slim 1.107.4, 2.27.1
  • pydantic pydantic_ai 1.107.4, 2.27.1
  • pydantic pydantic_ai_slim 1.107.4, 2.27.1

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-107293 updated cvss 4.3

pydantic-ai: pydantic-ai: Information disclosure via OpenTelemetry retry prompt logging

  • Red Hat Lightspeed Core lightspeed-core/lightspeed-stack-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-rocm-rhel9, rhelai3/bootc-gaudi-rhel9, rhelai3/disk-image-cuda-rhel9
    affected: workaround, no fix available “Fix deferred”

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
31 d ago

Exploit prediction

0.30% chance of exploitation in the next 30 days, higher than 22% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 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
CNA 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
NVD 3.1 5.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N

Affected packages

ecosystem package affected fixed in
pypi pydantic-ai
>=0.3.4, <1.107.4
>=2.0.0b1, <2.27.1
1.107.4
2.27.1
pypi pydantic-ai-slim
>=0.3.4, <1.107.4
>=2.0.0b1, <2.27.1
1.107.4
2.27.1

Affected products

  • pydantic pydantic-ai
  • pydantic pydantic-ai-slim

Classification

Weakness
  • CWE-212 Improper Removal of Sensitive Information Before Storage or Transfer
  • CWE-532 Insertion of Sensitive Information into Log File

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.