{"answers":{"affected":"3 open source packages ship an affected version, including langroid.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-54769 exists.","fix":"Upgrade langroid to 0.65.2 or later.","what":"CVE-2026-54769 is a critical code injection vulnerability in langroid, published on 9 Jul 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-2026-54769 and fix it if it is affected.\n\nWhat it is: CVE-2026-54769 is a critical code injection vulnerability in langroid, published on 9 Jul 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-2026-54769 exists.\n\nAffected packages and fixed versions:\n- langroid (PyPI): affected all versions; fixed in 0.65.2\n- langroid (PyPI): affected all versions; fixed in 0.65.2\n- langroid (PyPI): affected all versions; fixed in 0.65.2\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-2026-54769/ (Markdown: https://insights.sbomify.com/CVE-2026-54769/index.md)","id":"CVE-2026-54769","markdown":"https://insights.sbomify.com/CVE-2026-54769/index.md","name":"CVE-2026-54769","record":{"aliases":["GHSA-q9p7-wqxg-mrhc","PYSEC-2026-2581"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["code_execution"],"network_reachable":"yes","non_default_config":true,"product_category":"Python LLM framework","requires_auth":"none","summary":"Attackers can achieve remote code execution by exploiting incomplete sandboxing in eval() when processing LLM outputs in Langroid.","user_interaction":"not_required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[],"cvss":{"score":10,"severity":"critical","source":"cna","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","version":"3.1"},"cwes":[{"id":"CWE-94","name":"Improper Control of Generation of Code"}],"description":"Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution (RCE) in its `TableChatAgent` and `VectorStore` capabilities. When these agents evaluate LLM-generated tool messages with `full_eval=True`, they attempt to sandbox the execution by explicitly setting `locals` to an empty dictionary `{}` inside Python's `eval()` function. However, this relies on an incomplete understanding of Python's execution model. Because `__builtins__` is not explicitly scrubbed from the `globals` dictionary mapping, Python implicitly injects all built-ins during execution, granting full access to functions like `__import__('os').system()`. Since `TableChatAgent.pandas_eval()` executes external LLM outputs natively, this bypass permits any attacker providing prompt payload to achieve unauthenticated RCE on the host system. Version 0.65.2 patches the issue.","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: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent","id":"CVE-2026-54769","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"code_injection","year":"2026"},"n_packages":3,"n_references":1,"next":{"headline":"WebOb: Open redirect in Location header normalization via leading C0 control / space characters","id":"CVE-2026-54770"},"packages":[{"ecosystem":"PyPI","fixed":["0.65.2"],"introduced":["0"],"last_affected":[],"package":"langroid","purl":null,"source":"GHSA-q9p7-wqxg-mrhc"},{"ecosystem":"PyPI","fixed":["0.65.2"],"introduced":["0"],"last_affected":[],"package":"langroid","purl":"pkg:pypi/langroid","source":"GHSA-q9p7-wqxg-mrhc"},{"ecosystem":"PyPI","fixed":["0.65.2"],"introduced":["0"],"last_affected":[],"package":"langroid","purl":"pkg:pypi/langroid","source":"PYSEC-2026-2581"}],"prev":{"headline":"WPGraphQL has deprecated `user` field on SendPasswordResetEmailPayload that leaks user existence + profile (defeats explicit anti-enumeration design)","id":"CVE-2026-54768"},"products":["langroid"],"published":"2026-07-09","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":"total"},"state":"PUBLISHED","updated":"2026-07-10","vendors":["langroid"]},"summary":"Attackers can achieve remote code execution by exploiting incomplete sandboxing in eval() when processing LLM outputs in Langroid.","url":"https://insights.sbomify.com/CVE-2026-54769/"}