Code Injection in langroid (CVE-2026-54769)
Summary
Code injection in langroid (CVE-2026-54769). Successful exploitation can lead to full system takeover. Exploitable via TableChatAgent. Mitigation: upgrade to 0.65.2 or later.
Original description
The description as published by the source.
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.
Source: GitHub Security Advisories (Global) NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-54769 has been found in langroid.
Attackers can target a specific entry point like TableChatAgent over the network to misuse the product.
Successful exploitation can lead to full system takeover. CVSS score: 10.0/10.
What to do: upgrade langroid to 0.65.2 or later.
If unsure, ask your IT team or search "langroid CVE-2026-54769" on the vendor's site.
CVE-2026-54769 (langroid) — CWE-94 / CVSS v3 10.0
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Attack surface: TableChatAgent / VectorStore / locals / __builtins__
Patched: 0.65.2 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
Arbitrary code execution (CWE-94) exists in langroid. Attackers reach the vulnerable code path via TableChatAgent without authentication.
Check the vendor advisory for the affected versions of langroid. Attack surface: TableChatAgent / VectorStore / locals / __builtins__.
Severity: Critical (CVSS 10.0/10). Successful exploitation can lead to full system takeover.
Update to 0.65.2.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'langroid' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r 'langroid' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
langroidを grep し、稼働しているサービス・バージョンを把握する。 -
2Apply patch patch
Upgrade langroid to 0.65.2ステージング環境で 0.65.2 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスを含めること。
-
3Post-deployment verification verify
Confirm patched version is live in productionパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。
Affected packages
References
- advisory github.com
- advisory github.com
- advisory nvd.nist.gov
- package github.com
- web github.com