{"answers":{"affected":"3 open source packages ship an affected version, including text-generation.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-0599 exists.","fix":"Upgrade text-generation to 3.3.7 or later.","what":"CVE-2026-0599 is a high-severity denial of service vulnerability in huggingface/text-generation-inference, published on 2 Feb 2026. An attacker can exploit it over the internet without logging in, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-0599 and fix it if it is affected.\n\nWhat it is: CVE-2026-0599 is a high-severity denial of service vulnerability in huggingface/text-generation-inference, published on 2 Feb 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.\nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-0599 exists.\n\nAffected packages and fixed versions:\n- text-generation (PyPI): affected all versions; fixed in 3.3.7\n- text-generation (PyPI): affected all versions; fixed in 3.3.7\n- text-generation (PyPI): affected all versions; fixed in 3.3.7\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-2026-0599/ (Markdown: https://insights.sbomify.com/CVE-2026-0599/index.md)","id":"CVE-2026-0599","markdown":"https://insights.sbomify.com/CVE-2026-0599/index.md","name":"CVE-2026-0599","record":{"aliases":["GHSA-j7x9-7j54-2v3h","PYSEC-2026-1965"],"analysis":{"component_type":"server_software","fix_type":"upgrade","impacts":["denial_of_service"],"network_reachable":"yes","non_default_config":false,"product_category":"Text generation inference server","requires_auth":"none","summary":"Unauthenticated attackers can cause resource exhaustion and crash the server by triggering unbounded external image fetches during input validation.","user_interaction":"not_required","vuln_class":"denial_of_service"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"@huntr_ai","cpe":[],"cvss":{"score":7.5,"severity":"high","source":"cna","vector":"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","version":"3.0"},"cwes":[{"id":"CWE-400","name":"Uncontrolled Resource Consumption"}],"description":"A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET request, reading the entire response body into memory and cloning it before decoding. This behavior can lead to resource exhaustion, including network bandwidth saturation, memory inflation, and CPU overutilization. The vulnerability is triggered even if the request is later rejected for exceeding token limits. The default deployment configuration, which lacks memory usage limits and authentication, exacerbates the impact, potentially crashing the host machine. The issue is resolved in version 3.3.7.","ecosystems":["PyPI"],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"weaponised"},"has_fix":true,"headline":"Unbounded External Image Fetch in Validation Leads to Resource-Exhaustion DoS in huggingface/text-generation-inference","id":"CVE-2026-0599","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"denial_of_service","year":"2026"},"n_packages":3,"n_references":2,"next":{"headline":"Nexus Repository 3 - Server-Side Request Forgery in Proxy Repository Configuration","id":"CVE-2026-0600"},"packages":[{"ecosystem":"PyPI","fixed":["3.3.7"],"introduced":["0"],"last_affected":[],"package":"text-generation","purl":null,"source":"GHSA-j7x9-7j54-2v3h"},{"ecosystem":"PyPI","fixed":["3.3.7"],"introduced":["0"],"last_affected":[],"package":"text-generation","purl":"pkg:pypi/text-generation","source":"GHSA-j7x9-7j54-2v3h"},{"ecosystem":"PyPI","fixed":["3.3.7"],"introduced":["0"],"last_affected":[],"package":"text-generation","purl":"pkg:pypi/text-generation","source":"PYSEC-2026-1965"}],"prev":{"headline":"Missing authorization in Red Hat Ansible Automation Platform 2","id":"CVE-2026-0598"},"products":["huggingface/text-generation-inference"],"published":"2026-02-02","related":[],"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":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"}],"ssvc":{"automatable":"yes","exploitation":"poc","technical_impact":"partial"},"state":"PUBLISHED","updated":"2026-02-02","vendors":["huggingface"]},"summary":"Unauthenticated attackers can cause resource exhaustion and crash the server by triggering unbounded external image fetches during input validation.","url":"https://insights.sbomify.com/CVE-2026-0599/"}