dbcve.org
Code InjectionWeakness · CWE-94

CVE-2026-54769

CRITICAL · 10.0 CVSS v3.1 Published 2026-07-10
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
100/100
Remediation priority · Urgent
Remotely reachable No privileges Zero-click 6 weeks old

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
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.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

Langroid versions before 0.65.2 contain a sandbox escape vulnerability in TableChatAgent and VectorStore components. When these agents use eval() with full_eval=True and an empty locals dictionary to sandbox LLM-generated code, they fail to remove __builtins__ from the globals dictionary. Python implicitly includes all built-in functions, enabling attackers to call __import__('os').system() for unauthenticated remote code execution.

MitigationUpgrade Langroid to version 0.65.2 or later. If immediate patching is not possible, disable full_eval=True and implement input validation on LLM tool messages to prevent malicious payload injection.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Scope
Changed
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Identify installed Langroid version
    Run `pip show langroid` or `python -c "import langroid; print(langroid.__version__)"` to retrieve the installed version number
    Affected if The version is lower than 0.65.2
  2. Locate TableChatAgent usage
    Search codebase for imports like `from langroid.agent.specialist.table_chat_agent import TableChatAgent` or direct usage of TableChatAgent class
    Affected if TableChatAgent is imported or instantiated in your code
  3. Locate VectorStore usage
    Search codebase for imports like `from langroid.vector_store import ...` or instantiation of VectorStore-derived classes
    Affected if VectorStore component is imported or instantiated in your code
  4. Check full_eval configuration
    Search for `full_eval=True` in your codebase, particularly in eval() calls within agent configuration or tool message handling code
    Affected if full_eval=True is explicitly set or defaults to True in your agent setup

You are affected if you are running Langroid version below 0.65.2 AND using TableChatAgent or VectorStore with full_eval enabled, as this combination allows the unsafe eval() with unsanitized globals to execute.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Upgrade Langroid to version 0.65.2 or later. If immediate patching is not possible, disable full_eval=True and implement input validation on LLM tool messages to prevent malicious payload injection.

Recommended fix Moderate confidence

langroid version 0.65.2

  1. 1. Identify the current version of Langroid in your project by checking your dependency files (e.g., requirements.txt, pyproject.toml, or poetry.lock)
  2. 2. Upgrade Langroid to version 0.65.2 or later by running: pip install langroid>=0.65.2 (or your equivalent package manager command)
  3. 3. Verify the upgrade was successful by checking the installed version: pip show langroid
  4. 4. If your project uses TableChatAgent or VectorStore capabilities, review your code to ensure you understand how eval() is being called - confirm the patch properly scrubs __builtins__ from globals
  5. 5. Test your application to ensure the upgrade does not break existing functionality

Generated from the published advisory — verify against the referenced sources before acting.

Have this fixed Scoped from the published advisory
  • Consultation4.0 h
  • Implementation8.0 h
  • Testing4.0 h
  • Review / QA2.0 h
18.0 hours of engineering $3,200
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $5,120.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-54769 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

Get it on GitHub Scan in the browser

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-54769 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data