{"id":"CVE-2026-107294","aliases":["EUVD-2026-95104","GHSA-v2xh-2vp8-57h8","PYSEC-2026-4280","PYSEC-2026-4289"],"status":"published","title":"Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl","description":"Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.2 and 2.24.0, web_fetch_tool, the WebFetch local fallback, and remote FileUrl media downloads buffer the complete HTTP response body before enforcing content-size controls. An attacker-influenced URL can stream an arbitrarily large response that exhausts process memory and crashes the worker; affected media types include ImageUrl, DocumentUrl, VideoUrl, and AudioUrl. SSRF protections remain effective, and the impact is limited to availability. This issue is fixed in versions 1.107.2 and 2.24.0.","severity":{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-12","score":0.00437,"percentile":0.38454,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-400","CWE-770"],"published":"2026-10-08T16:59:25Z","modified":"2026-10-28T02:30:30Z","fixes":[{"ecosystem":"PyPI","package":"pydantic-ai","fixed_in":["1.107.2","2.24.0"],"sources":["ghsa","osv"]},{"ecosystem":"PyPI","package":"pydantic-ai-slim","fixed_in":["1.107.2","2.24.0"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"pydantic-ai","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"1.77.0"},{"fixed":"1.107.2"}]}]},{"source":"ghsa","ecosystem":"PyPI","package":"pydantic-ai","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"2.0.0b1"},{"last_affected":"2.23.0"},{"fixed":"2.24.0"}]}]},{"source":"ghsa","ecosystem":"PyPI","package":"pydantic-ai-slim","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"1.77.0"},{"fixed":"1.107.2"}]}]},{"source":"ghsa","ecosystem":"PyPI","package":"pydantic-ai-slim","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"2.0.0b1"},{"last_affected":"2.23.0"},{"fixed":"2.24.0"}]}]},{"source":"osv","ecosystem":"PyPI","package":"pydantic-ai","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"1.77.0"},{"fixed":"1.107.2"}]}],"versions":["1.100.0","1.101.0","1.102.0","1.103.0","1.104.0","1.105.0","1.106.0","1.107.0","1.107.1","1.77.0","1.78.0","1.79.0","1.80.0","1.81.0","1.82.0","1.83.0","1.84.0","1.84.1","1.85.0","1.85.1","1.86.0","1.86.1","1.87.0","1.88.0","1.89.0","1.89.1","1.90.0","1.91.0","1.92.0","1.93.0","1.94.0","1.95.0","1.95.1","1.96.0","1.96.1","1.97.0","1.98.0","1.99.0"]},{"source":"osv","ecosystem":"PyPI","package":"pydantic-ai","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"2.0.0b1"},{"fixed":"2.24.0"}]}],"versions":["2.0.0","2.0.0b1","2.0.0b2","2.0.0b3","2.0.0b4","2.0.0b5","2.0.0b6","2.0.0b7","2.1.0","2.10.0","2.11.0","2.12.0","2.13.0","2.14.0","2.14.1","2.15.0","2.16.0","2.17.0","2.18.0","2.19.0","2.2.0","2.20.0","2.21.0","2.22.0","2.23.0","2.3.0","2.4.0","2.5.0","2.5.1","2.6.0","2.7.0","2.8.0","2.9.0","2.9.1"]},{"source":"osv","ecosystem":"PyPI","package":"pydantic-ai-slim","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"1.77.0"},{"fixed":"1.107.2"}]}],"versions":["1.100.0","1.101.0","1.102.0","1.103.0","1.104.0","1.105.0","1.106.0","1.107.0","1.107.1","1.77.0","1.78.0","1.79.0","1.80.0","1.81.0","1.82.0","1.83.0","1.84.0","1.84.1","1.85.0","1.85.1","1.86.0","1.86.1","1.87.0","1.88.0","1.89.0","1.89.1","1.90.0","1.91.0","1.92.0","1.93.0","1.94.0","1.95.0","1.95.1","1.96.0","1.96.1","1.97.0","1.98.0","1.99.0"]},{"source":"osv","ecosystem":"PyPI","package":"pydantic-ai-slim","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"2.0.0b1"},{"fixed":"2.24.0"}]}],"versions":["2.0.0","2.0.0b1","2.0.0b2","2.0.0b3","2.0.0b4","2.0.0b5","2.0.0b6","2.0.0b7","2.1.0","2.10.0","2.11.0","2.12.0","2.13.0","2.14.0","2.14.1","2.15.0","2.16.0","2.17.0","2.18.0","2.19.0","2.2.0","2.20.0","2.21.0","2.22.0","2.23.0","2.3.0","2.4.0","2.5.0","2.5.1","2.6.0","2.7.0","2.8.0","2.9.0","2.9.1"]},{"source":"osv","ecosystem":"PyPI","package":"pydantic-ai","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"1.77.0"},{"fixed":"1.107.2"},{"introduced":"2.0.0b1"},{"fixed":"2.24.0"}]}],"versions":["1.100.0","1.101.0","1.102.0","1.103.0","1.104.0","1.105.0","1.106.0","1.107.0","1.107.1","1.77.0","1.78.0","1.79.0","1.80.0","1.81.0","1.82.0","1.83.0","1.84.0","1.84.1","1.85.0","1.85.1","1.86.0","1.86.1","1.87.0","1.88.0","1.89.0","1.89.1","1.90.0","1.91.0","1.92.0","1.93.0","1.94.0","1.95.0","1.95.1","1.96.0","1.96.1","1.97.0","1.98.0","1.99.0","2.0.0","2.0.0b1","2.0.0b2","2.0.0b3","2.0.0b4","2.0.0b5","2.0.0b6","2.0.0b7","2.1.0","2.10.0","2.11.0","2.12.0","2.13.0","2.14.0","2.14.1","2.15.0","2.16.0","2.17.0","2.18.0","2.19.0","2.2.0","2.20.0","2.21.0","2.22.0","2.23.0","2.3.0","2.4.0","2.5.0","2.5.1","2.6.0","2.7.0","2.8.0","2.9.0","2.9.1"]},{"source":"osv","ecosystem":"PyPI","package":"pydantic-ai-slim","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"1.77.0"},{"fixed":"1.107.2"},{"introduced":"2.0.0b1"},{"fixed":"2.24.0"}]}],"versions":["1.100.0","1.101.0","1.102.0","1.103.0","1.104.0","1.105.0","1.106.0","1.107.0","1.107.1","1.77.0","1.78.0","1.79.0","1.80.0","1.81.0","1.82.0","1.83.0","1.84.0","1.84.1","1.85.0","1.85.1","1.86.0","1.86.1","1.87.0","1.88.0","1.89.0","1.89.1","1.90.0","1.91.0","1.92.0","1.93.0","1.94.0","1.95.0","1.95.1","1.96.0","1.96.1","1.97.0","1.98.0","1.99.0","2.0.0","2.0.0b1","2.0.0b2","2.0.0b3","2.0.0b4","2.0.0b5","2.0.0b6","2.0.0b7","2.1.0","2.10.0","2.11.0","2.12.0","2.13.0","2.14.0","2.14.1","2.15.0","2.16.0","2.17.0","2.18.0","2.19.0","2.2.0","2.20.0","2.21.0","2.22.0","2.23.0","2.3.0","2.4.0","2.5.0","2.5.1","2.6.0","2.7.0","2.8.0","2.9.0","2.9.1"]}],"products":[{"vendor":"pydantic","product":"pydantic-ai"},{"vendor":"pydantic","product":"pydantic-ai-slim"},{"vendor":"pydantic","product":"pydantic_ai"}],"references":[{"url":"https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-v2xh-2vp8-57h8","tags":["x_refsource_CONFIRM","Vendor Advisory","advisory","web"]},{"url":"https://github.com/pydantic/pydantic-ai/pull/7141","tags":["x_refsource_MISC","Patch","Issue Tracking","fix","web"]},{"url":"https://github.com/pydantic/pydantic-ai/pull/7308","tags":["x_refsource_MISC","Patch","Issue Tracking","fix","web"]},{"url":"https://github.com/pydantic/pydantic-ai/commit/7a64d049c3f5271a975cd1d64b2fa876d83ede1d","tags":["x_refsource_MISC","Patch","fix","web"]},{"url":"https://github.com/pydantic/pydantic-ai/commit/e3824a58c82864ed26afb2887619834a4eb86cc8","tags":["x_refsource_MISC","Patch","fix","web"]},{"url":"https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.2","tags":["x_refsource_MISC","Patch","Release Notes","web"]},{"url":"https://github.com/pydantic/pydantic-ai/releases/tag/v2.24.0","tags":["x_refsource_MISC","Patch","Release Notes","Vendor Advisory","web"]},{"url":"https://github.com/advisories/GHSA-v2xh-2vp8-57h8","tags":["advisory"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/107xxx/CVE-2026-107294.json","tags":["advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-107294","tags":["advisory"]},{"url":"https://github.com/pydantic/pydantic-ai","tags":["package"]},{"url":"https://pypi.org/project/pydantic-ai","tags":["package"]},{"url":"https://pypi.org/project/pydantic-ai-slim","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2026-107294","title":"Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl","description":"Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.2 and 2.24.0, web_fetch_tool, the WebFetch local fallback, and remote FileUrl media downloads buffer the complete HTTP response body before enforcing content-size controls. An attacker-influenced URL can stream an arbitrarily large response that exhausts process memory and crashes the worker; affected media types include ImageUrl, DocumentUrl, VideoUrl, and AudioUrl. SSRF protections remain effective, and the impact is limited to availability. This issue is fixed in versions 1.107.2 and 2.24.0.","status":"published","published":"2026-10-08T16:59:25.246Z","modified":"2026-10-09T15:15:18.765Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium","assessor":"cna"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T13:45:14.072357Z"}],"euvd":[{"id":"EUVD-2026-95104","description":"Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.2 and 2.24.0, web_fetch_tool, the WebFetch local fallback, and remote FileUrl media downloads buffer the complete HTTP response body before enforcing content-size controls. An attacker-influenced URL can stream an arbitrarily large response that exhausts process memory and crashes the worker; affected media types include ImageUrl, DocumentUrl, VideoUrl, and AudioUrl. SSRF protections remain effective, and the impact is limited to availability. This issue is fixed in versions 1.107.2 and 2.24.0.","status":"published","published":"2026-10-08T16:59:25Z","modified":"2026-10-09T15:15:18Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"updated_at":"2026-11-02T17:27:25.010362Z"}],"ghsa":[{"id":"GHSA-v2xh-2vp8-57h8","title":"Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl","description":"### Summary\n\nSeveral remote-content download paths in Pydantic AI buffered the entire HTTP response body into memory before enforcing any size limit. An application that exposes the local web-fetch tool (`web_fetch_tool`, or the `WebFetch` capability's local fallback) to untrusted prompts can be driven to fetch an attacker-chosen URL that streams a very large body, exhausting process memory and crashing the worker. The same unbounded buffering applied to `FileUrl` media downloads (`ImageUrl`, `DocumentUrl`, `VideoUrl`, `AudioUrl`).\n\nThis is an **availability** issue only. SSRF protections (scheme allowlist, private-IP and cloud-metadata blocking) are unaffected; there is no confidentiality or integrity impact.\n\n### Details\n\nThe download helpers read the full response body before applying content-size controls, so an existing text-length limit only truncated *after* the whole body was already in memory, and media downloads had no wire-level cap at all. A single large response could grow process memory without bound .\n\n### Who Is Affected\n\nYou are affected if your application registers the local web-fetch tool (or relies on the `WebFetch` capability's local fallback) and exposes the agent to untrusted prompts, or if it downloads large remote `FileUrl`s influenced by untrusted input. Applications that only fetch developer-controlled URLs are not exposed to the model-chosen attack path.\n\n### Remediation\n\nUpgrade to `2.24.0` or later (v2) or `1.107.2` or later (v1). Patched versions enforce a default 50 MiB cap on web-fetch and `FileUrl` downloads while streaming; pass `None` to the limit to restore the previous unbounded behavior.\n\n### Credits\n\nIdentified during internal review of media-download hardening.","status":"published","published":"2026-10-08T17:16:28Z","modified":"2026-10-08T17:16:28Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"cwes":["CWE-400","CWE-770"],"updated_at":"2026-11-02T14:41:30.097746Z"}],"nvd":[{"id":"CVE-2026-107294","description":"Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.2 and 2.24.0, web_fetch_tool, the WebFetch local fallback, and remote FileUrl media downloads buffer the complete HTTP response body before enforcing content-size controls. An attacker-influenced URL can stream an arbitrarily large response that exhausts process memory and crashes the worker; affected media types include ImageUrl, DocumentUrl, VideoUrl, and AudioUrl. SSRF protections remain effective, and the impact is limited to availability. This issue is fixed in versions 1.107.2 and 2.24.0.","status":"published","published":"2026-10-08T17:17:15.08Z","modified":"2026-10-13T13:49:02.473Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium","assessor":"secondary"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T14:12:55.142936Z"}],"osv":[{"id":"CVE-2026-107294","title":"Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl","description":"Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.2 and 2.24.0, web_fetch_tool, the WebFetch local fallback, and remote FileUrl media downloads buffer the complete HTTP response body before enforcing content-size controls. An attacker-influenced URL can stream an arbitrarily large response that exhausts process memory and crashes the worker; affected media types include ImageUrl, DocumentUrl, VideoUrl, and AudioUrl. SSRF protections remain effective, and the impact is limited to availability. This issue is fixed in versions 1.107.2 and 2.24.0.","status":"published","published":"2026-10-08T16:59:25.246Z","modified":"2026-10-28T02:30:30.389109025Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T15:44:54.933106Z"},{"id":"GHSA-v2xh-2vp8-57h8","title":"Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl","description":"### Summary\n\nSeveral remote-content download paths in Pydantic AI buffered the entire HTTP response body into memory before enforcing any size limit. An application that exposes the local web-fetch tool (`web_fetch_tool`, or the `WebFetch` capability's local fallback) to untrusted prompts can be driven to fetch an attacker-chosen URL that streams a very large body, exhausting process memory and crashing the worker. The same unbounded buffering applied to `FileUrl` media downloads (`ImageUrl`, `DocumentUrl`, `VideoUrl`, `AudioUrl`).\n\nThis is an **availability** issue only. SSRF protections (scheme allowlist, private-IP and cloud-metadata blocking) are unaffected; there is no confidentiality or integrity impact.\n\n### Details\n\nThe download helpers read the full response body before applying content-size controls, so an existing text-length limit only truncated *after* the whole body was already in memory, and media downloads had no wire-level cap at all. A single large response could grow process memory without bound .\n\n### Who Is Affected\n\nYou are affected if your application registers the local web-fetch tool (or relies on the `WebFetch` capability's local fallback) and exposes the agent to untrusted prompts, or if it downloads large remote `FileUrl`s influenced by untrusted input. Applications that only fetch developer-controlled URLs are not exposed to the model-chosen attack path.\n\n### Remediation\n\nUpgrade to `2.24.0` or later (v2) or `1.107.2` or later (v1). Patched versions enforce a default 50 MiB cap on web-fetch and `FileUrl` downloads while streaming; pass `None` to the limit to restore the previous unbounded behavior.\n\n### Credits\n\nIdentified during internal review of media-download hardening.","status":"published","published":"2026-10-08T17:16:28Z","modified":"2026-10-15T14:55:51.016328589Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"cwes":["CWE-400","CWE-770"],"updated_at":"2026-11-02T15:46:56.639206Z"},{"id":"PYSEC-2026-4280","title":"Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl","description":"### Summary\n\nSeveral remote-content download paths in Pydantic AI buffered the entire HTTP response body into memory before enforcing any size limit. An application that exposes the local web-fetch tool (`web_fetch_tool`, or the `WebFetch` capability's local fallback) to untrusted prompts can be driven to fetch an attacker-chosen URL that streams a very large body, exhausting process memory and crashing the worker. The same unbounded buffering applied to `FileUrl` media downloads (`ImageUrl`, `DocumentUrl`, `VideoUrl`, `AudioUrl`).\n\nThis is an **availability** issue only. SSRF protections (scheme allowlist, private-IP and cloud-metadata blocking) are unaffected; there is no confidentiality or integrity impact.\n\n### Details\n\nThe download helpers read the full response body before applying content-size controls, so an existing text-length limit only truncated *after* the whole body was already in memory, and media downloads had no wire-level cap at all. A single large response could grow process memory without bound .\n\n### Who Is Affected\n\nYou are affected if your application registers the local web-fetch tool (or relies on the `WebFetch` capability's local fallback) and exposes the agent to untrusted prompts, or if it downloads large remote `FileUrl`s influenced by untrusted input. Applications that only fetch developer-controlled URLs are not exposed to the model-chosen attack path.\n\n### Remediation\n\nUpgrade to `2.24.0` or later (v2) or `1.107.2` or later (v1). Patched versions enforce a default 50 MiB cap on web-fetch and `FileUrl` downloads while streaming; pass `None` to the limit to restore the previous unbounded behavior.\n\n### Credits\n\nIdentified during internal review of media-download hardening.","status":"published","published":"2026-10-15T10:22:51.092652Z","modified":"2026-10-15T14:55:51.016328589Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"updated_at":"2026-11-02T15:52:57.671918Z"},{"id":"PYSEC-2026-4289","title":"Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl","description":"### Summary\n\nSeveral remote-content download paths in Pydantic AI buffered the entire HTTP response body into memory before enforcing any size limit. An application that exposes the local web-fetch tool (`web_fetch_tool`, or the `WebFetch` capability's local fallback) to untrusted prompts can be driven to fetch an attacker-chosen URL that streams a very large body, exhausting process memory and crashing the worker. The same unbounded buffering applied to `FileUrl` media downloads (`ImageUrl`, `DocumentUrl`, `VideoUrl`, `AudioUrl`).\n\nThis is an **availability** issue only. SSRF protections (scheme allowlist, private-IP and cloud-metadata blocking) are unaffected; there is no confidentiality or integrity impact.\n\n### Details\n\nThe download helpers read the full response body before applying content-size controls, so an existing text-length limit only truncated *after* the whole body was already in memory, and media downloads had no wire-level cap at all. A single large response could grow process memory without bound .\n\n### Who Is Affected\n\nYou are affected if your application registers the local web-fetch tool (or relies on the `WebFetch` capability's local fallback) and exposes the agent to untrusted prompts, or if it downloads large remote `FileUrl`s influenced by untrusted input. Applications that only fetch developer-controlled URLs are not exposed to the model-chosen attack path.\n\n### Remediation\n\nUpgrade to `2.24.0` or later (v2) or `1.107.2` or later (v1). Patched versions enforce a default 50 MiB cap on web-fetch and `FileUrl` downloads while streaming; pass `None` to the limit to restore the previous unbounded behavior.\n\n### Credits\n\nIdentified during internal review of media-download hardening.","status":"published","published":"2026-10-15T10:22:51.184366Z","modified":"2026-10-15T14:55:51.016328589Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"updated_at":"2026-11-02T15:52:57.671918Z"}]}}