{"answers":{"affected":"3 open source packages ship an affected version, including langroid. It affects 1 product.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-25481 exists.","fix":"Upgrade langroid to 0.59.32 or later.","what":"CVE-2026-25481 is a critical code injection vulnerability in langroid, published on 4 Feb 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-2026-25481 and fix it if it is affected.\n\nWhat it is: CVE-2026-25481 is a critical code injection vulnerability in langroid, published on 4 Feb 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: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-25481 exists.\n\nAffected packages and fixed versions:\n- langroid (PyPI): affected all versions; fixed in 0.59.32\n- langroid (PyPI): affected all versions; fixed in 0.59.32\n- langroid (PyPI): affected all versions; fixed in 0.59.32\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-2026-25481/ (Markdown: https://insights.sbomify.com/CVE-2026-25481/index.md)","id":"CVE-2026-25481","markdown":"https://insights.sbomify.com/CVE-2026-25481/index.md","name":"CVE-2026-25481","record":{"aliases":["GHSA-x34r-63hx-w57f","PYSEC-2026-383"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["code_execution"],"network_reachable":"yes","non_default_config":false,"product_category":"Langroid LLM framework","requires_auth":"none","summary":"Attackers can bypass WAF restrictions in TableChatAgent to execute arbitrary code via unsafe pandas_eval expressions.","user_interaction":"required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[{"product":"langroid","vendor":"langroid"}],"cvss":{"score":9.4,"severity":"critical","source":"cna","vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H","version":"4.0"},"cwes":[{"id":"CWE-94","name":"Improper Control of Generation of Code"}],"description":"Langroid is a framework for building large-language-model-powered applications. Prior to version 0.59.32, there is a bypass to the fix for CVE-2025-46724. TableChatAgent can call pandas_eval tool to evaluate the expression. There is a WAF in langroid/utils/pandas_utils.py introduced to block code injection CVE-2025-46724. However it can be bypassed due to _literal_ok() returning False instead of raising UnsafeCommandError on invalid input, combined with unrestricted access to dangerous dunder attributes (__init__, __globals__, __builtins__). This allows chaining whitelisted DataFrame methods to leak the eval builtin and execute arbitrary code. This issue has been patched in version 0.59.32.","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":"Langroid has WAF Bypass Leading to RCE in TableChatAgent","id":"CVE-2026-25481","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"code_injection","year":"2026"},"n_packages":3,"n_references":3,"next":{"headline":"Craft Commerce has Stored DOM XSS in Order Status Name (Reflects in \"Recent Orders\" Dashboard Widget)","id":"CVE-2026-25482"},"packages":[{"ecosystem":"PyPI","fixed":["0.59.32"],"introduced":["0"],"last_affected":[],"package":"langroid","purl":null,"source":"GHSA-x34r-63hx-w57f"},{"ecosystem":"PyPI","fixed":["0.59.32"],"introduced":["0"],"last_affected":[],"package":"langroid","purl":"pkg:pypi/langroid","source":"GHSA-x34r-63hx-w57f"},{"ecosystem":"PyPI","fixed":["0.59.32"],"introduced":["0"],"last_affected":[],"package":"langroid","purl":"pkg:pypi/langroid","source":"PYSEC-2026-383"}],"prev":{"headline":"FileStore key canonicalization collisions allow response cache mixup/poisoning (ASCII ord + Unicode NFKD)","id":"CVE-2026-25480"},"products":["langroid"],"published":"2026-02-04","related":[{"cvss_score":9.8,"headline":"Langroid has a Code Injection vulnerability in TableChatAgent","id":"CVE-2025-46724","kev_date_added":null,"published":"2025-05-20"},{"cvss_score":8.1,"headline":"Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store","id":"CVE-2025-46725","kev_date_added":null,"published":"2025-05-20"},{"cvss_score":7.8,"headline":"Langroid Vulnerable to XXE Injection via XMLToolMessage","id":"CVE-2025-46726","kev_date_added":null,"published":"2025-05-05"}],"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":"yes","exploitation":"poc","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-02-04","vendors":["langroid"]},"summary":"Attackers can bypass WAF restrictions in TableChatAgent to execute arbitrary code via unsafe pandas_eval expressions.","url":"https://insights.sbomify.com/CVE-2026-25481/"}