{"id":"CVE-2026-107293","title":"Pydantic AI is a Python agent framework for building applications and workflows with Generative AI","summary":"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 exp…","severity":"low","cvss":2.3,"cvssVector":"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","cwe":["CWE-212","CWE-532"],"vendor":"pydantic-ai","product":"pydantic-ai","affected":["pydantic-ai >= 0.3.4, < 1.107.4","pydantic-ai >= 2.0.0b1, < 2.27.1","pydantic-ai-slim >= 0.3.4, < 1.107.4","pydantic-ai-slim >= 2.0.0b1, < 2.27.1"],"patched":["pydantic-ai 1.107.4","pydantic-ai 2.27.1","pydantic-ai-slim 1.107.4","pydantic-ai-slim 2.27.1"],"published":"2026-10-08","updated":"2026-10-08","sourceUpdated":"2026-10-08T20:35:31.200","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-107293","references":[{"url":"https://github.com/pydantic/pydantic-ai/commit/fe9dbed7b7ccf7e7128b5786886e4441f6f5594f","label":"security-advisories@github.com"},{"url":"https://github.com/pydantic/pydantic-ai/pull/7357","label":"security-advisories@github.com"},{"url":"https://github.com/pydantic/pydantic-ai/releases/tag/v2.27.1","label":"security-advisories@github.com"},{"url":"https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-3gh4-cghq-f8v4","label":"security-advisories@github.com"},{"url":"https://github.com/advisories/GHSA-3gh4-cghq-f8v4"}],"tags":["nvd","ghsa","pip","cve.org"],"aliases":["GHSA-3gh4-cghq-f8v4"],"ecosystem":"pip","ssvc":{"exploitation":"none","automatable":"no","technicalImpact":"partial","timestamp":"2026-10-08T17:14:19.566455Z"},"cvssSource":"cna","ingestedAt":"2026-10-08T17:56:11.713Z","slug":"CVE-2026-107293","body":"## Overview\n\nPydantic 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.\n\n## Remediation\n\nRefer to the linked advisories for vendor-supplied fixes and affected version ranges.\n\n## Package advisory (CVE-2026-107293)\n\nAffected packages:\n\n- `pydantic-ai >= 0.3.4, < 1.107.4`\n- `pydantic-ai >= 2.0.0b1, < 2.27.1`\n- `pydantic-ai-slim >= 0.3.4, < 1.107.4`\n- `pydantic-ai-slim >= 2.0.0b1, < 2.27.1`\n\nPatched in:\n\n- `pydantic-ai 1.107.4`\n- `pydantic-ai 2.27.1`\n- `pydantic-ai-slim 1.107.4`\n- `pydantic-ai-slim 2.27.1`\n\nSource: https://github.com/advisories/GHSA-3gh4-cghq-f8v4","depth":"sunlit","depthScore":13,"depthScoreParts":{"impact":12.6,"likelihood":0,"exploitation":0,"ransomware":0},"changes":[]}