Langroid: handle_message() executes user-supplied tool JSON without sender verification

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

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

EPSS

• CVE-2026-54771: 0.39% estimated exploitation activity in the next 30 days; percentile 33.37 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Summary 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. Details enablemessage(..., use=False, handle=True) only prevents the LLM from being instructed to generate the tool. The tool dispatch path in agentresponse() → handlemessage() → gettoolmessages() does not check whether the message originated from Entity.USER or Entity.LLM: langroid/agent/base.py As a result, a user who sends raw tool JSON as chat input can directly invoke the handler. PoC The following script demonstrates that a tool registered with use=False, handle=True can still be invoked directly by a user-supplied chat message. Observed result: agent.gettoolmessages(usermsg) returns the parsed tool and agent.handlemessage(usermsg) executes it, even though hastoolmessageattempt(usermsg) returns False for USER-origin messages. Impact Depending on which handled tools are enabled, the impact…

Published by the source

6 Jul 2026, 20:42 UTC

Last modified by the source

13 Jul 2026, 16:43 UTC

Source last checked

26 Oct 2026, 13:46 UTC

1. Revision 2 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-gjgq-w2m6-wr5q

2. Revision 1 · created · 24 Oct 2026

   Published from osv record GHSA-gjgq-w2m6-wr5q

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-54771

Advisory: Langroid: handle_message() executes user-supplied tool JSON without sender verification
IDs: CVE-2026-54771, GHSA-gjgq-w2m6-wr5q
Record: https://patchnext.com/advisories/cve-2026-54771 (revision 2, source checked 26 Oct 2026, 13:46 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: High (CVSS 8.1)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: langroid 0.65.3. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI langroid: affected <= 0.65.2; fixed in 0.65.3

## Suggested inspection (read-only)
- `python -m pip show langroid`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on langroid.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-gjgq-w2m6-wr5q (OSV record GHSA-gjgq-w2m6-wr5q lists affected ranges: PyPI langroid >=0 <0.65.3 (fixed))
- Verified: https://github.com/advisories/GHSA-gjgq-w2m6-wr5q (GitHub-reviewed advisory GHSA-gjgq-w2m6-wr5q lists affected ranges: PyPI langroid >=0 <=0.65.2)

Commands are suggestions: review each one before running it.