CVE-2026-107293
Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`
Auswirkung
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.
Ein Angreifer kann die Lücke über das Netzwerk ausnutzen, ohne Anmeldung, ohne Zutun eines Nutzers. Bei Erfolg: geringes Risiko, dass Daten ausgelesen werden.
Betroffene Pakete
| Ökosystem | Paket | Betroffen | Behoben in |
|---|---|---|---|
| pip | pydantic-ai | >= 0.3.4, < 1.107.4 | 1.107.4 |
| pip | pydantic-ai-slim | >= 0.3.4, < 1.107.4 | 1.107.4 |
Betroffene Produkte · Pydantic
| Produkt | Betroffene Versionen |
|---|---|
| Pydantic Ai | ab 0.3.4 vor 1.107.4 ab 2.0.0 vor 2.27.1 |
Schwachstellenklasse
Referenzen
- NVD-Eintrag
- CVE.org-Eintrag
- GitHub-Advisory
- https://github.com/advisories/GHSA-3gh4-cghq-f8v4
- 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