Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`
CVE-2026-107293 · GHSA-3gh4-cghq-f8v4 · published 2026-10-08
- Severity
- Low
- CVSS score
- 2.3
- Chance of exploitation (EPSS)
- 0.30%
- Fixed in
- 2.27.1
- Exploitation No known exploitation
- Automatable No
- Technical impact Partial
- CISA SSVC
This does not grant an attacker any new access to the agent or its data: the content is only visible to whoever can read the exported telemetry. The exposure matters when traces are exported to a destination whose audience is broader or less trusted than the agent's own data — a third-party observability vendor or a shared backend — which is the scenario include_content=False exists for. The disclosed content is limited to retry feedback: validation error details, which can quote invalid values from the model's output, or output-validator ModelRetry messages.
Upgrade pydantic-ai to 2.27.1 or later, and pydantic-ai-slim to 2.27.1 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
Upgrade to a patched version; retry prompt content now honors include_content=False like all other message content. If you rely on this setting, consider reviewing previously exported traces for retry prompt content that should not have been recorded.
If you cannot upgrade, scrub or drop the message attributes (gen_ai.input.messages, gen_ai.output.messages, pydantic_ai.all_messages) in your telemetry pipeline (for example with an OpenTelemetry Collector processor), or use tool-based structured output modes, whose retry feedback honors include_content=False.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| pydantic-ai | PyPI | >= 0.3.4, < 1.107.4 | 1.107.4 |
| pydantic-ai | PyPI | >= 2.0.0b1, < 2.27.1 | 2.27.1 |
| pydantic-ai-slim | PyPI | >= 0.3.4, < 1.107.4 | 1.107.4 |
| pydantic-ai-slim | PyPI | >= 2.0.0b1, < 2.27.1 | 2.27.1 |
- CriticalPhoenix: Format String Injection in applyChatTemplatearize-phoenix
- CriticalFlowise: Unauthenticated OAuth2 token refresh endpoint returns access tokens — enables token theft for any connected serviceflowise
- CriticalMLflow: Environment variable injection in AI Gateway secrets enables server-side credential exfiltrationmlflow
- CriticalvLLM has RCE In Video Processingvllm
- HighConfig revision hashes could expose password verifiersopenclaw
- Highn8n: Shared Credential Header Leak via HTTP Request Pagination Expressionn8n, n8n, n8n
- HighPydantic AI: Concurrency-limited models can keep their slot when a streamed request ends earlypydantic-ai, pydantic-ai-slim
- HighPydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execupydantic-ai, pydantic-ai, pydantic-ai-slim, pydantic-ai-slim
- HighPydantic AI has Server-Side Request Forgery (SSRF) in URL Download Handlingpydantic-ai, pydantic-ai-slim
- HighPydantic AI has Stored XSS via Path Traversal in Web UI CDN URLpydantic-ai, pydantic-ai-slim
- MediumPydantic AI: Event loop blocked by quadratic title extraction in `web_fetch`pydantic-ai, pydantic-ai, pydantic-ai-slim, pydantic-ai-slim
- MediumPydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the local chat endpoint does not validate the `Host` headerpydantic-ai, pydantic-ai, pydantic-ai-slim, pydantic-ai-slim
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.