CWE-75Weakness · CWE-75

CVE-2026-54771

HIGH · 8.1 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 →
87/100
Remediation priority · High
Remotely reachable 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. Prior to version 0.65.3, a Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with `use=False, handle=True`. Version 0.65.3 fixes 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 is a framework for building LLM-powered applications. Prior to version 0.65.3, the framework allows direct tool invocation via raw JSON payloads even when tools are registered with `use=False, handle=True`, bypassing intended access controls and allowing untrusted users to execute arbitrary tool operations.

MitigationUpgrade Langroid to version 0.65.3 or later to remediate this vulnerability.

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
Low
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
None

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

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 `pip list | grep langroid` to check the installed version
    Affected if Version is lower than 0.65.3 (e.g., 0.65.2, 0.64.0, etc.)
  2. Locate tool registration code
    Search source code files for tool registration patterns, specifically looking for `use=False` and `handle=True` parameters in tool setup (e.g., grep for 'use=False' or 'handle=True' in Python files using Langroid)
    Affected if Tools are registered with `use=False, handle=True` configuration, which enables the vulnerable bypass path
  3. Identify raw JSON tool invocation endpoints
    Search for API route handlers or endpoints that accept JSON payloads for tool calls (look for FastAPI/Flask routes accepting tool invocation requests, JSON body parsers, or tool-related endpoints)
    Affected if Application exposes an endpoint that accepts raw JSON tool invocation payloads without additional access control checks
  4. Check for tool dispatch logic
    Inspect the tool dispatch or execution logic in the codebase to verify if it validates tool accessibility before execution when tools are configured with `handle=True`
    Affected if Tool dispatch does not enforce access controls for tools registered with `use=False, handle=True` when processing raw JSON payloads

You are affected if you are running Langroid versions prior to 0.65.3 AND your application has tools registered with `use=False, handle=True` AND exposes an interface that allows raw JSON tool invocation without proper access validation.

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 0.65.3 or later to remediate this vulnerability.

Recommended fix High confidence

0.65.3

  1. Check the current installed version of Langroid in your environment (e.g., pip show langroid or pip list)
  2. Upgrade Langroid to version 0.65.3 or later using pip install langroid>=0.65.3 or pip install --upgrade langroid
  3. Verify the installed version is 0.65.3 or newer
  4. Test that tool invocation behaves correctly with use=False, handle=True configuration

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

Have this fixed Scoped from the published advisory
  • Consultation1.0 h
  • Implementation1.0 h
  • Testing2.0 h
  • Review / QA1.0 h
5.0 hours of engineering $860
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $1,376.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-54771 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

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-2026-54771 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