CVE-2026-107293— Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`
Quick assessment
Affected
pydantic pydantic-ai
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.
Pydantic AI 是一个用于基于生成式人工智能构建应用程序和工作流的 Python 智能体框架。在版本 0.3.4 至 1.107.3，以及 2.27.0 中，当使用 配置 OpenTelemetry 仪器化功能时，工具调用（tool calls）之外的重试提示（retry prompts）可能被导出到 和 中。因此，使用 NativeOutput、PromptedOutput 或对文本输出进行验证的输出验证器的智能体，可能会向遥测后端（telemetry backend）的访问者泄露验证反馈信息，包括该反馈
Possible ATT&CK Techniques 1 AI
T1530 · Data from Cloud StorageAffected Version Matrix 4
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| pydantic | pydantic-ai | >= 0.3.4, < 1.107.4 |
affected |
>= 2.0.0b1, < 2.27.1 |
affected | ||
| pydantic | pydantic-ai-slim | >= 0.3.4, < 1.107.4 |
affected |
>= 2.0.0b1, < 2.27.1 |
affected |
Get alerts for future matching vulnerabilities
Log in to subscribe
I. Basic Information for CVE-2026-107293
Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
Vulnerability Title
Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`
Source: CVE Program / CVE List V5
Vulnerability Description
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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N
Source: CVE Program / CVE List V5
Vulnerability Type
敏感数据的不恰当跨边界移除
Source: CVE Program / CVE List V5
Affected Products
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| pydantic | pydantic-ai | >= 0.3.4, < 1.107.4 | - |
|
| pydantic | pydantic-ai-slim | >= 0.3.4, < 1.107.4 | - |
|
II. Public POCs for CVE-2026-107293
| # | POC Description | Source Link | Shenlong Link |
|---|
AI-Generated POC
Premium
No public POC found.
Login to generate AI POCIII. Intelligence Information for CVE-2026-107293
请登录查看更多情报信息。
Patches & Fixes for CVE-2026-107293 (2)
Other References for CVE-2026-107293 (2)
-
🔗 Release v2.27.1 (2026-08-10) · pydantic/pydantic-ai · GitHub x_refsource_MISC
-
Same Patch Batch · pydantic · 2026-10-08 · 10 CVEs total
| CVE-2026-107295 | 7.6 HIGH | `pydantic-ai-slim` web UI `/api/chat` accepts browser-simple cross-origin requests that ca |
| CVE-2026-107286 | 7.5 HIGH | Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends e |
| CVE-2026-107289 | 6.8 MEDIUM | Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv6 zone identifier (incomplete fix |
| CVE-2026-107287 | 6.5 MEDIUM | Pydantic AI: Excessive resource use when local web fetching converts nested HTML |
| CVE-2026-107290 | 6.5 MEDIUM | Pydantic AI: Event loop blocked by quadratic title extraction in `web_fetch` |
| CVE-2026-107294 | 6.5 MEDIUM | Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl |
| CVE-2026-107292 | 6.4 MEDIUM | Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the local chat endpoint does not v |
| CVE-2026-107288 | 3.7 LOW | Pydantic AI: web_fetch_tool blocked_domains bypass via a hostname the resolver normalizes |
| CVE-2026-107291 | 2.3 LOW | Pydantic AI OpenTelemetry instrumentation: exception events on tool and agent run spans in |
IV. Related Vulnerabilities
Same product: pydantic-ai
-
CVE-2026-107295
`pydantic-ai-slim` web UI `/api/chat` accepts browser-simple -
CVE-2026-107294
Pydantic AI: Unbounded memory use when downloading remote co -
CVE-2026-107292
Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the -
CVE-2026-107291
Pydantic AI OpenTelemetry instrumentation: exception events -
CVE-2026-107290
Pydantic AI: Event loop blocked by quadratic title extractio
Same vendor: pydantic
-
CVE-2026-107295
`pydantic-ai-slim` web UI `/api/chat` accepts browser-simple -
CVE-2026-107294
Pydantic AI: Unbounded memory use when downloading remote co -
CVE-2026-107292
Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the -
CVE-2026-107291
Pydantic AI OpenTelemetry instrumentation: exception events -
CVE-2026-107290
Pydantic AI: Event loop blocked by quadratic title extractio
Same weakness: CWE-212
-
CVE-2026-107291
Pydantic AI OpenTelemetry instrumentation: exception events -
CVE-2026-96879
"Checked by" label in page history should not be shown if th -
CVE-2026-17511
This Power System update is being released to address -
CVE-2026-90860
Canva鸿蒙版1.15.1前WebView会话劫持漏洞 -
CVE-2026-67071
HCL DevOps Deploy / HCL Launch is susceptible to an Improper
V. Comments for CVE-2026-107293
No comments yet