{"answers":{"affected":"10 open source packages ship an affected version, including pydantic-ai and pydantic-ai-slim. It affects 1 product.","exploited":"There is no known exploitation of CVE-2026-107287 in the wild and no public exploit code.","fix":"Upgrade pydantic-ai to a fixed version for your release line: 1.107.7 or 2.52.0.","what":"CVE-2026-107287 is a medium-severity denial of service vulnerability in pydantic-ai, published on 8 Oct 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link."},"fix_prompt":"Check this codebase for CVE-2026-107287 and fix it if it is affected.\n\nWhat it is: CVE-2026-107287 is a medium-severity denial of service vulnerability in pydantic-ai, published on 8 Oct 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.\nExploitation: There is no known exploitation of CVE-2026-107287 in the wild and no public exploit code.\n\nAffected packages and fixed versions:\n- pydantic-ai (PyPI): affected from 1.77.0; fixed in 1.107.7, 2.52.0\n- pydantic-ai (PyPI): affected from 1.77.0; fixed in 1.107.7\n- pydantic-ai (PyPI): affected from 1.77.0; fixed in 1.107.7\n- pydantic-ai (PyPI): affected from 2.0.0b1; fixed in 2.52.0\n- pydantic-ai (PyPI): affected from 2.0.0b1; fixed in 2.52.0\n- pydantic-ai-slim (PyPI): affected from 1.77.0; fixed in 1.107.7, 2.52.0\n- pydantic-ai-slim (PyPI): affected from 1.77.0; fixed in 1.107.7\n- pydantic-ai-slim (PyPI): affected from 1.77.0; fixed in 1.107.7\n- pydantic-ai-slim (PyPI): affected from 2.0.0b1; fixed in 2.52.0\n- pydantic-ai-slim (PyPI): affected from 2.0.0b1; fixed in 2.52.0\n\nTask:\n1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.\n2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.\n3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.\n4. Run the tests and summarise what changed and why.\n5. If nothing in the project is affected, say so and change nothing.\n\nReference: https://insights.sbomify.com/CVE-2026-107287/ (Markdown: https://insights.sbomify.com/CVE-2026-107287/index.md)","id":"CVE-2026-107287","markdown":"https://insights.sbomify.com/CVE-2026-107287/index.md","name":"CVE-2026-107287","record":{"aliases":["CLEANSTART-2026-HS78493","GHSA-v36g-jcw9-x7cw","PYSEC-2026-4281","PYSEC-2026-4290"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["denial_of_service"],"network_reachable":"yes","non_default_config":false,"product_category":"Python AI agent framework","requires_auth":"none","summary":"Attackers can cause excessive CPU and memory consumption in Pydantic AI via deeply nested HTML during local web fetching, leading to denial of service.","user_interaction":"required","vuln_class":"denial_of_service"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[{"product":"pydantic_ai","vendor":"pydantic"}],"cvss":{"score":6.5,"severity":"medium","source":"cna","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","version":"3.1"},"cwes":[{"id":"CWE-407","name":"Inefficient Algorithmic Complexity"},{"id":"CWE-400","name":"Uncontrolled Resource Consumption"}],"description":"Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.7 and 2.52.0, the local web_fetch_tool and the WebFetch local fallback can consume excessive CPU and memory during HTML-to-Markdown conversion of attacker-controlled HTML containing deeply nested block elements. Conversion repeatedly reprocesses accumulated text and can greatly expand intermediate output before the returned-content limit is applied, allowing a model-directed fetch to delay other work in the process. Provider-native web fetching is not affected. This issue is fixed in versions 1.107.7 and 2.52.0.","ecosystems":["PyPI"],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"none_known"},"has_fix":true,"headline":"Pydantic AI: Excessive resource use when local web fetching converts nested HTML","id":"CVE-2026-107287","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"denial_of_service","year":"2026"},"n_packages":10,"n_references":7,"next":{"headline":"Pydantic AI: web_fetch_tool blocked_domains bypass via a hostname the resolver normalizes differently","id":"CVE-2026-107288"},"packages":[{"ecosystem":"PyPI","fixed":["1.107.7","2.52.0"],"introduced":["1.77.0","2.0.0b1"],"last_affected":[],"package":"pydantic-ai","purl":"pkg:pypi/pydantic-ai","source":"PYSEC-2026-4281"},{"ecosystem":"PyPI","fixed":["1.107.7"],"introduced":["1.77.0"],"last_affected":[],"package":"pydantic-ai","purl":null,"source":"GHSA-v36g-jcw9-x7cw"},{"ecosystem":"PyPI","fixed":["1.107.7"],"introduced":["1.77.0"],"last_affected":[],"package":"pydantic-ai","purl":"pkg:pypi/pydantic-ai","source":"GHSA-v36g-jcw9-x7cw"},{"ecosystem":"PyPI","fixed":["2.52.0"],"introduced":["2.0.0b1"],"last_affected":[],"package":"pydantic-ai","purl":null,"source":"GHSA-v36g-jcw9-x7cw"},{"ecosystem":"PyPI","fixed":["2.52.0"],"introduced":["2.0.0b1"],"last_affected":[],"package":"pydantic-ai","purl":"pkg:pypi/pydantic-ai","source":"GHSA-v36g-jcw9-x7cw"},{"ecosystem":"PyPI","fixed":["1.107.7","2.52.0"],"introduced":["1.77.0","2.0.0b1"],"last_affected":[],"package":"pydantic-ai-slim","purl":"pkg:pypi/pydantic-ai-slim","source":"PYSEC-2026-4290"},{"ecosystem":"PyPI","fixed":["1.107.7"],"introduced":["1.77.0"],"last_affected":[],"package":"pydantic-ai-slim","purl":null,"source":"GHSA-v36g-jcw9-x7cw"},{"ecosystem":"PyPI","fixed":["1.107.7"],"introduced":["1.77.0"],"last_affected":[],"package":"pydantic-ai-slim","purl":"pkg:pypi/pydantic-ai-slim","source":"GHSA-v36g-jcw9-x7cw"},{"ecosystem":"PyPI","fixed":["2.52.0"],"introduced":["2.0.0b1"],"last_affected":[],"package":"pydantic-ai-slim","purl":null,"source":"GHSA-v36g-jcw9-x7cw"},{"ecosystem":"PyPI","fixed":["2.52.0"],"introduced":["2.0.0b1"],"last_affected":[],"package":"pydantic-ai-slim","purl":"pkg:pypi/pydantic-ai-slim","source":"GHSA-v36g-jcw9-x7cw"}],"prev":{"headline":"Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends early","id":"CVE-2026-107286"},"products":["pydantic-ai","pydantic-ai-slim"],"published":"2026-10-08","related":[{"cvss_score":8.6,"headline":"Pydantic AI Affected by Server-Side Request Forgery (SSRF) in URL Download Handling","id":"CVE-2026-25580","kev_date_added":null,"published":"2026-02-06"},{"cvss_score":7.6,"headline":"Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint","id":"CVE-2026-107295","kev_date_added":null,"published":"2026-10-08"},{"cvss_score":7.5,"headline":"Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends early","id":"CVE-2026-107286","kev_date_added":null,"published":"2026-10-08"},{"cvss_score":7.1,"headline":"Pydantic AI affected by Stored XSS via Path Traversal in Web UI CDN URL","id":"CVE-2026-25640","kev_date_added":null,"published":"2026-02-06"},{"cvss_score":6.8,"headline":"Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv6 zone identifiers","id":"CVE-2026-107289","kev_date_added":null,"published":"2026-10-08"},{"cvss_score":6.8,"headline":"Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv4-mapped IPv6 (Incomplete fix of CVE-2026-25580)","id":"CVE-2026-46678","kev_date_added":null,"published":"2026-07-29"},{"cvss_score":6.8,"headline":"Pydantic AI: Unvalidated UploadedFile references in UI adapters allow server-side file access using the application's credentials","id":"CVE-2026-54249","kev_date_added":null,"published":"2026-07-29"}],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"class":"attribution","licence":"CC BY 4.0","name":"GitHub Advisory Database","prefix":"GHSA"},{"class":"attribution","licence":"CC BY 4.0","name":"PyPA Advisory Database","prefix":"PYSEC"},{"class":"attribution","licence":"US public information, NVD API terms","name":"NVD"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"}],"ssvc":{"automatable":"no","exploitation":"none","technical_impact":"partial"},"state":"PUBLISHED","updated":"2026-10-14","vendors":["pydantic"]},"summary":"Attackers can cause excessive CPU and memory consumption in Pydantic AI via deeply nested HTML during local web fetching, leading to denial of service.","url":"https://insights.sbomify.com/CVE-2026-107287/"}