CVE-2026-107291Medium· 4.3▾ SunlitPydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.3.4 until 1.107.6 and 2.44.0, OpenTelemetry instrumentation configured with InstrumentationSettings(include_content=False) can sti…
▾ Sunlit zone — Low / medium · no exploitation signal
impact 23.7 · likelihood 0.1 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Stakeholder-Specific Vulnerability Categorization from CISA's ADP record at CVE.org: whether exploitation is observed, whether an attack can be automated, and how much of the system is at stake.
Exploit-prediction probability, daily snapshots since Oct 10.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
0.4%
Last analysed / modified upstream
2.3 → 4.3
low → medium
0.4% → 0.6%
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.3.4 until 1.107.6 and 2.44.0, OpenTelemetry instrumentation configured with InstrumentationSettings(include_content=False) can still export sensitive agent content through exception.message and exception.stacktrace events, error status descriptions, and model_request_parameters containing instructions or the prompted_output_template. The exposed data is available to readers of the configured telemetry backend and can include tool feedback, provider error bodies, runtime instructions, and structured-output templates even though message attributes are redacted. This issue does not grant new access to agent data, and deployments that do not use include_content=False are not affected by the setting bypass. This issue is fixed in versions 1.107.6 and 2.44.0.
pydantic_ai >= 0.3.4, < 1.107.4pydantic_ai >= 2.0.0, < 2.44.0Upgrade past the affected range:
pydantic_ai 2.44.0Affected packages:
pydantic-ai >= 0.3.4, < 1.107.6pydantic-ai >= 2.0.0b1, < 2.44.0pydantic-ai-slim >= 0.3.4, < 1.107.6pydantic-ai-slim >= 2.0.0b1, < 2.44.0Patched in:
pydantic-ai 1.107.6pydantic-ai 2.44.0pydantic-ai-slim 1.107.6pydantic-ai-slim 2.44.0Field changes observed since this record was first indexed.
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-107293Medium· 5.3Pydantic AI is a Python agent framework for building applications and workflows with Generative AI
CVE-2026-107289Medium· 6.8Pydantic AI is a Python agent framework for building applications and workflows with Generative AI
CVE-2026-107295High· 7.6Pydantic AI is a Python agent framework for building applications and workflows with Generative AI
CVE-2026-107294Medium· 6.5Pydantic AI is a Python agent framework for building applications and workflows with Generative AI
CVE-2026-107292Medium· 6.4Pydantic AI is a Python agent framework for building applications and workflows with Generative AI
CVE-2026-107290Medium· 6.5Pydantic AI is a Python agent framework for building applications and workflows with Generative AI