{"answers":{"affected":"3 open source packages ship an affected version, including langflow. It affects 1 product.","exploited":"There is no known exploitation of CVE-2026-33873 in the wild and no public exploit code.","fix":"Upgrade langflow to 1.9.0 or later.","what":"CVE-2026-33873 is a critical code injection vulnerability in Langflow Langflow, published on 27 Mar 2026. Any signed-in user can exploit it over the network, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-33873 and fix it if it is affected.\n\nWhat it is: CVE-2026-33873 is a critical code injection vulnerability in Langflow Langflow, published on 27 Mar 2026. Any signed-in user can exploit it over the network, with no action from the victim.\nExploitation: There is no known exploitation of CVE-2026-33873 in the wild and no public exploit code.\n\nAffected packages and fixed versions:\n- langflow (PyPI): affected all versions; fixed in 1.9.0\n- langflow (PyPI): affected all versions; fixed in 1.9.0\n- langflow (PyPI): affected all versions; fixed in 1.9.0\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-2026-33873/ (Markdown: https://insights.sbomify.com/CVE-2026-33873/index.md)","id":"CVE-2026-33873","markdown":"https://insights.sbomify.com/CVE-2026-33873/index.md","name":"CVE-2026-33873","record":{"aliases":["ECHO-e568-958c-ec51","GHSA-v8hw-mh8c-jxfc","PYSEC-2026-82"],"analysis":{"component_type":"web_application","fix_type":"upgrade","impacts":["code_execution"],"network_reachable":"yes","non_default_config":false,"product_category":"AI workflow builder","requires_auth":"low_privilege","summary":"Authenticated attackers can execute arbitrary Python code on the server by influencing LLM output in the Agentic Assistant validation phase.","user_interaction":"not_required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[{"product":"langflow","vendor":"langflow"}],"cvss":{"score":9.3,"severity":"critical","source":"cna","vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:H/SI:H/SA:N","version":"4.0"},"cwes":[{"id":"CWE-94","name":"Improper Control of Generation of Code"}],"description":"Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the implementation reaches dynamic execution sinks and instantiates the generated class server-side. In deployments where an attacker can access the Agentic Assistant feature and influence the model output, this can result in arbitrary server-side Python execution. Version 1.9.0 fixes the issue.","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":"Langflow has Authenticated Code Execution in Agentic Assistant Validation","id":"CVE-2026-33873","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":"langflow:langflow","products":["langflow:langflow"],"type":"code_injection","year":"2026"},"n_packages":3,"n_references":16,"next":{"headline":"Authenticator vulnerable to Remote Code Execution","id":"CVE-2026-33874"},"packages":[{"ecosystem":"PyPI","fixed":["1.9.0"],"introduced":["0"],"last_affected":[],"package":"langflow","purl":null,"source":"GHSA-v8hw-mh8c-jxfc"},{"ecosystem":"PyPI","fixed":["1.9.0"],"introduced":["0"],"last_affected":[],"package":"langflow","purl":"pkg:pypi/langflow","source":"GHSA-v8hw-mh8c-jxfc"},{"ecosystem":"PyPI","fixed":["1.9.0"],"introduced":["0"],"last_affected":[],"package":"langflow","purl":"pkg:pypi/langflow","source":"PYSEC-2026-82"}],"prev":{"headline":"elixir-nodejs has Cross-User Data Leakage or Information Disclosure due to Worker Protocol Race Condition","id":"CVE-2026-33872"},"products":["langflow"],"published":"2026-03-27","related":[{"cvss_score":9.8,"headline":"IBM Langflow Code Injection","id":"CVE-2026-9198","kev_date_added":"2026-08-04","published":"2026-07-17"},{"cvss_score":9.8,"headline":"Langflow Inclusion of Functionality from Untrusted Control Sphere","id":"CVE-2026-0770","kev_date_added":"2026-07-21","published":"2026-01-23"},{"cvss_score":9.8,"headline":"Langflow Missing Authentication","id":"CVE-2025-3248","kev_date_added":"2025-05-05","published":"2025-04-07"},{"cvss_score":9.4,"headline":"Langflow Origin Validation Error","id":"CVE-2025-34291","kev_date_added":"2026-05-21","published":"2025-12-05"},{"cvss_score":9.3,"headline":"Langflow Code Injection","id":"CVE-2026-33017","kev_date_added":"2026-03-25","published":"2026-03-20"},{"cvss_score":8.4,"headline":"Langflow Authorization Bypass Through User-Controlled Key","id":"CVE-2026-55255","kev_date_added":"2026-07-07","published":"2026-06-23"},{"cvss_score":10,"headline":"Unauthenticated Server-Side RCE via PythonCodeStructuredTool in Public Flows","id":"CVE-2026-10134","kev_date_added":null,"published":"2026-06-30"}],"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":"total"},"state":"PUBLISHED","updated":"2026-04-02","vendors":["langflow-ai"]},"summary":"Authenticated attackers can execute arbitrary Python code on the server by influencing LLM output in the Agentic Assistant validation phase.","url":"https://insights.sbomify.com/CVE-2026-33873/"}