https://vulnerability.circl.lu Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Fri, 09 Oct 2026 16:49:22 +0000 https://vulnerability.circl.lu/vuln/cve-2026-107293 <p><strong>Affected:</strong> pydantic-ai, pydantic-ai-slim</p> <p>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.</p> <p><strong>Affected:</strong> pydantic-ai, pydantic-ai-slim</p> <p>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.</p> https://vulnerability.circl.lu/vuln/cve-2026-107293 https://vulnerability.circl.lu/vuln/ghsa-3gh4-cghq-f8v4 <p><strong>Affected:</strong> PyPI: pydantic-ai, PyPI: pydantic-ai-slim</p> <p>### Summary</p> <p>Pydantic AI&#39;s OpenTelemetry instrumentation supports `InstrumentationSettings(include_content=False)` to exclude message content — user prompts, model completions, tool call arguments and responses — from exported telemetry, so that agents can be monitored without sending sensitive content to the observability backend.</p> <p>Retry prompts — the feedback messages Pydantic AI sends back to the model when its output fails validation or an output validator raises `ModelRetry` — were not covered by this setting when they were not associated with a tool call, as with structured output modes that don&#39;t use tool calls (e.g. `NativeOutput` or `PromptedOutput`) and output validators applied to text output. Their full content was recorded on model request spans even with `include_content=False`. Since validation feedback can quote invalid values from the model&#39;s response, message content that the setting was configured to withhold could reach the telemetry backend.</p> <p>### Details</p> <p>Retry prompts without an associated tool call were serialized into span message attributes (such as `gen_ai.input.messages` and `pydantic_ai.all_messages`) as regular text parts, and this path did not apply the `include_content` check that every other message part applies. Retry prompts tied to a tool call, and all other message content, were redacted correctly.</p> <p>### Impact</p> <p>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 expor…</p> <p><strong>Affected:</strong> PyPI: pydantic-ai, PyPI: pydantic-ai-slim</p> <p>### Summary</p> <p>Pydantic AI&#39;s OpenTelemetry instrumentation supports `InstrumentationSettings(include_content=False)` to exclude message content — user prompts, model completions, tool call arguments and responses — from exported telemetry, so that agents can be monitored without sending sensitive content to the observability backend.</p> <p>Retry prompts — the feedback messages Pydantic AI sends back to the model when its output fails validation or an output validator raises `ModelRetry` — were not covered by this setting when they were not associated with a tool call, as with structured output modes that don&#39;t use tool calls (e.g. `NativeOutput` or `PromptedOutput`) and output validators applied to text output. Their full content was recorded on model request spans even with `include_content=False`. Since validation feedback can quote invalid values from the model&#39;s response, message content that the setting was configured to withhold could reach the telemetry backend.</p> <p>### Details</p> <p>Retry prompts without an associated tool call were serialized into span message attributes (such as `gen_ai.input.messages` and `pydantic_ai.all_messages`) as regular text parts, and this path did not apply the `include_content` check that every other message part applies. Retry prompts tied to a tool call, and all other message content, were redacted correctly.</p> <p>### Impact</p> <p>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 expor…</p> https://vulnerability.circl.lu/vuln/ghsa-3gh4-cghq-f8v4