{"answers":{"affected":"3 open source packages ship an affected version, including langchain-openai. It affects 1 product.","exploited":"There is no known exploitation of CVE-2026-41488 in the wild and no public exploit code.","fix":"Upgrade langchain-openai to 1.1.14 or later.","what":"CVE-2026-41488 is a low-severity server-side request forgery vulnerability in langchain-ai langchain-openai, published on 24 Apr 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-2026-41488 and fix it if it is affected.\n\nWhat it is: CVE-2026-41488 is a low-severity server-side request forgery vulnerability in langchain-ai langchain-openai, published on 24 Apr 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-2026-41488 in the wild and no public exploit code.\n\nAffected packages and fixed versions:\n- langchain-openai (PyPI): affected all versions; fixed in 1.1.14\n- langchain-openai (PyPI): affected all versions; fixed in 1.1.14\n- langchain-openai (PyPI): affected all versions; fixed in 1.1.14\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-2026-41488/ (Markdown: https://insights.sbomify.com/CVE-2026-41488/index.md)","id":"CVE-2026-41488","markdown":"https://insights.sbomify.com/CVE-2026-41488/index.md","name":"CVE-2026-41488","record":{"aliases":["ECHO-7a3a-0a91-96a1","GHSA-r7w7-9xr2-qq2r","PYSEC-2026-76"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["data_read","security_bypass"],"network_reachable":"yes","non_default_config":false,"product_category":"LangChain OpenAI library","requires_auth":"none","summary":"Attackers can bypass SSRF protections in LangChain OpenAI via DNS rebinding to access internal network resources during image token counting.","user_interaction":"required","vuln_class":"ssrf"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[{"product":"langchain-openai","vendor":"langchain"}],"cvss":{"score":3.1,"severity":"low","source":"cna","vector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:N/A:N","version":"3.1"},"cwes":[{"id":"CWE-918","name":"Server-Side Request Forgery"}],"description":"LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai's _url_to_size() helper (used by get_num_tokens_from_messages for image token counting) validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS resolution. This left a TOCTOU / DNS rebinding window: an attacker-controlled hostname could resolve to a public IP during validation and then to a private/localhost IP during the actual fetch.","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":"angchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding","id":"CVE-2026-41488","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"ssrf","year":"2026"},"n_packages":3,"n_references":1,"next":{"headline":"Pi-hole: Local privilege escalation via config-controlled path in root-executed service hooks","id":"CVE-2026-41489"},"packages":[{"ecosystem":"PyPI","fixed":["1.1.14"],"introduced":["0"],"last_affected":[],"package":"langchain-openai","purl":null,"source":"GHSA-r7w7-9xr2-qq2r"},{"ecosystem":"PyPI","fixed":["1.1.14"],"introduced":["0"],"last_affected":[],"package":"langchain-openai","purl":"pkg:pypi/langchain-openai","source":"GHSA-r7w7-9xr2-qq2r"},{"ecosystem":"PyPI","fixed":["1.1.14"],"introduced":["0"],"last_affected":[],"package":"langchain-openai","purl":"pkg:pypi/langchain-openai","source":"PYSEC-2026-76"}],"prev":{"headline":"Missing authorization in langfuse","id":"CVE-2026-41487"},"products":["langchain-openai"],"published":"2026-04-24","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":"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":"2026-04-27","vendors":["langchain-ai"]},"summary":"Attackers can bypass SSRF protections in LangChain OpenAI via DNS rebinding to access internal network resources during image token counting.","url":"https://insights.sbomify.com/CVE-2026-41488/"}