CVE-2026-107291
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.
Does this matter?
Lower severity and a low EPSS score (0.62%). 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 1.107.6 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.
- 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
- 0.62% probability · 50th 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 0.4% on 9 October 2026 to 0.6% on 26 October 2026.
References
- https://github.com/pydantic/pydantic-ai/commit/4e013c51a50659aba2adf7853bfb22bb77f6a518Patch
- https://github.com/pydantic/pydantic-ai/commit/6b14c74cb281f899a2ae4fae5327111e33f60771Patch
- https://github.com/pydantic/pydantic-ai/commit/7ee27e38ab2e525ca60ff1a25d16413ff989fd79Patch
- https://github.com/pydantic/pydantic-ai/commit/963dec5f70d6f558997fc259356c0090cc5ea487Patch
- https://github.com/pydantic/pydantic-ai/commit/de4e61515327bd80a19cd8552001c30933e6acc3Patch
- https://github.com/pydantic/pydantic-ai/pull/8403Patch, Vendor Advisory
- https://github.com/pydantic/pydantic-ai/pull/8404Patch, Vendor Advisory
- https://github.com/pydantic/pydantic-ai/pull/8408Patch, Vendor Advisory
- https://github.com/pydantic/pydantic-ai/pull/8428Patch, Vendor Advisory
- https://github.com/pydantic/pydantic-ai/pull/8429Exploit, Patch, Vendor Advisory
- https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.6Patch, Release Notes, Vendor Advisory
- https://github.com/pydantic/pydantic-ai/releases/tag/v2.44.0Patch, Release Notes, Vendor Advisory
- https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-4x9p-g9wm-8q7fMitigation, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.