VAITP Dataset

← Back to the dataset

CVE-2026-107293

OpenTelemetry may leak validation feedback via retry prompts in Pydantic AI telemetry.

  • CVSS 2.3
  • CWE-212
  • Information Leakage
  • Remote

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 base score
2.3
Published
2026-10-08
OWASP
A09 Security Logging and Monitoring Failures
Orthogonal defect classification
Interface
Code defect classification
Incorrect Interface
Category
Information Leakage
Subcategory
Information Disclosure
Accessibility scope
Remote
Impact
Information Disclosure
Affected component
Python
Fixed by upgrading
Yes

Solution

Upgrade Pydantic AI to version 1.107.4 or later (or 2.27.1 or later).

Vulnerable code sample

from pydantic_ai import Agent, NativeOutput
from pydantic_ai.instrumentation import InstrumentationSettings, configure_instrumentation

# VULNERABLE: include_content=False leaks validation feedback
settings = InstrumentationSettings(include_content=False)
configure_instrumentation(settings)

class EchoAgent(Agent):
    def handle(self, user_input: str) -> NativeOutput:
        # This validation error message can be leaked via telemetry
        if len(user_input) > 200:
            raise ValueError(f"Input too long: {len(user_input)} characters")
        return NativeOutput(content=user_input)

Patched code sample

from pydantic_ai import Agent, NativeOutput
from pydantic_ai.instrumentation import InstrumentationSettings, configure_instrumentation

# FIX: include_content=True prevents leaking validation feedback
settings = InstrumentationSettings(include_content=True)
configure_instrumentation(settings)

class EchoAgent(Agent):
    def handle(self, user_input: str) -> NativeOutput:
        # This validation error message is no longer exported in telemetry
        if len(user_input) > 200:
            raise ValueError(f"Input too long: {len(user_input)} characters")
        return NativeOutput(content=user_input)

Published fix

Public sources link this CVE to the changes below. The code samples above were generated to illustrate the defect; these links lead to the code the project actually changed.

Cite this entry

@misc{vaitp:cve2026107293,
  title        = {{OpenTelemetry may leak validation feedback via retry prompts in Pydantic AI telemetry.}},
  author       = {Bogaerts, Fr\'ed\'eric and Ivaki, Naghmeh and Fonseca, Jos\'e},
  year         = {2026},
  note         = {VAITP Python Vulnerability Dataset, entry CVE-2026-107293},
  howpublished = {\url{https://netpack.pt/vaitp/vulnerability/CVE-2026-107293/}}
}

Download this entry as JSON Download the whole dataset

Introducing the "VAITP dataset": a specialized repository of Python vulnerabilities and patches, meticulously compiled for the use of the security research community. As Python's prominence grows, understanding and addressing potential security vulnerabilities become crucial. Crafted by and for the cybersecurity community, this dataset offers a valuable resource for researchers, analysts, and developers to analyze and mitigate the security risks associated with Python. Through the comprehensive exploration of vulnerabilities and corresponding patches, the VAITP dataset fosters a safer and more resilient Python ecosystem, encouraging collaborative advancements in programming security.

The supreme art of war is to subdue the enemy without fighting.

Sun Tzu – “The Art of War”

:: Shaping the future through research and ingenuity ::

Before you use the VAITP AI models

Please read and accept the following disclaimer:

By choosing "I understand and accept", you acknowledge that you understand and agree to these terms.