CVE-2026-107293 (GCVE-0-2026-107293)
Vulnerability from cvelistv5
Published
2026-10-08 16:57
Modified
2026-10-08 17:14
Severity ?
2.3 (Low) - 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 - Improper Removal of Sensitive Information Before Storage or Transfer
  • CWE-532 - Insertion of Sensitive Information into Log File
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 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.
References
Impacted products
Vendor Product Version
pydantic pydantic-ai Version: >= 0.3.4, < 1.107.4
Version: >= 2.0.0b1, < 2.27.1
 Create a notification for this product.
   pydantic pydantic-ai-slim Version: >= 0.3.4, < 1.107.4
Version: >= 2.0.0b1, < 2.27.1
 Create a notification for this product.
Show details on NVD website

To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-107293",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-10-08T17:14:19.566455Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-10-08T17:14:30.659Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "pydantic-ai",
          "vendor": "pydantic",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 0.3.4, \u003c 1.107.4"
            },
            {
              "status": "affected",
              "version": "\u003e= 2.0.0b1, \u003c 2.27.1"
            }
          ]
        },
        {
          "product": "pydantic-ai-slim",
          "vendor": "pydantic",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 0.3.4, \u003c 1.107.4"
            },
            {
              "status": "affected",
              "version": "\u003e= 2.0.0b1, \u003c 2.27.1"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "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."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "PRESENT",
            "attackVector": "NETWORK",
            "baseScore": 2.3,
            "baseSeverity": "LOW",
            "privilegesRequired": "LOW",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "vectorString": "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",
            "version": "4.0",
            "vulnAvailabilityImpact": "NONE",
            "vulnConfidentialityImpact": "LOW",
            "vulnIntegrityImpact": "NONE"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-212",
              "description": "CWE-212: Improper Removal of Sensitive Information Before Storage or Transfer",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-532",
              "description": "CWE-532: Insertion of Sensitive Information into Log File",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-10-08T16:57:24.841Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-3gh4-cghq-f8v4",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-3gh4-cghq-f8v4"
        },
        {
          "name": "https://github.com/pydantic/pydantic-ai/pull/7357",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/pull/7357"
        },
        {
          "name": "https://github.com/pydantic/pydantic-ai/commit/fe9dbed7b7ccf7e7128b5786886e4441f6f5594f",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/commit/fe9dbed7b7ccf7e7128b5786886e4441f6f5594f"
        },
        {
          "name": "https://github.com/pydantic/pydantic-ai/releases/tag/v2.27.1",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v2.27.1"
        }
      ],
      "source": {
        "advisory": "GHSA-3gh4-cghq-f8v4",
        "discovery": "UNKNOWN"
      },
      "title": "Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-107293",
    "datePublished": "2026-10-08T16:57:24.841Z",
    "dateReserved": "2026-10-07T15:53:23.586Z",
    "dateUpdated": "2026-10-08T17:14:30.659Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-107293\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-10-08T17:14:19.566455Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-10-08T17:14:25.899Z\"}}], \"cna\": {\"title\": \"Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`\", \"source\": {\"advisory\": \"GHSA-3gh4-cghq-f8v4\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV4_0\": {\"version\": \"4.0\", \"baseScore\": 2.3, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"LOW\", \"vectorString\": \"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\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"attackRequirements\": \"PRESENT\", \"privilegesRequired\": \"LOW\", \"subIntegrityImpact\": \"NONE\", \"vulnIntegrityImpact\": \"NONE\", \"subAvailabilityImpact\": \"NONE\", \"vulnAvailabilityImpact\": \"NONE\", \"subConfidentialityImpact\": \"NONE\", \"vulnConfidentialityImpact\": \"LOW\"}}], \"affected\": [{\"vendor\": \"pydantic\", \"product\": \"pydantic-ai\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003e= 0.3.4, \u003c 1.107.4\"}, {\"status\": \"affected\", \"version\": \"\u003e= 2.0.0b1, \u003c 2.27.1\"}]}, {\"vendor\": \"pydantic\", \"product\": \"pydantic-ai-slim\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003e= 0.3.4, \u003c 1.107.4\"}, {\"status\": \"affected\", \"version\": \"\u003e= 2.0.0b1, \u003c 2.27.1\"}]}], \"references\": [{\"url\": \"https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-3gh4-cghq-f8v4\", \"name\": \"https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-3gh4-cghq-f8v4\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/pydantic/pydantic-ai/pull/7357\", \"name\": \"https://github.com/pydantic/pydantic-ai/pull/7357\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/pydantic/pydantic-ai/commit/fe9dbed7b7ccf7e7128b5786886e4441f6f5594f\", \"name\": \"https://github.com/pydantic/pydantic-ai/commit/fe9dbed7b7ccf7e7128b5786886e4441f6f5594f\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/pydantic/pydantic-ai/releases/tag/v2.27.1\", \"name\": \"https://github.com/pydantic/pydantic-ai/releases/tag/v2.27.1\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"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.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-212\", \"description\": \"CWE-212: Improper Removal of Sensitive Information Before Storage or Transfer\"}]}, {\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-532\", \"description\": \"CWE-532: Insertion of Sensitive Information into Log File\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-10-08T16:57:24.841Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-107293\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-10-08T17:14:30.659Z\", \"dateReserved\": \"2026-10-07T15:53:23.586Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-10-08T16:57:24.841Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
  • Confirmed: The vulnerability is confirmed from an analyst perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
  • Patched: This vulnerability was successfully patched by the user reporting the sighting.
  • Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
  • Not confirmed: The user expresses doubt about the veracity of the vulnerability.
  • Not patched: This vulnerability was not successfully patched by the user reporting the sighting.