CVE-2026-54771: Langroid: handle_message() executes user-supplied tool JSON without sender verification

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 enable_message(...,…

8.1CVSS Score

HIGHSeverity

NOCISA KEV

VulnerabilityImpact Type

📋 Vulnerability Details

CVE ID	CVE-2026-54771
Vendor	pip
Affected Product	langroid
Vulnerability Type	Vulnerability
CVSS Score	8.1 (HIGH)
Actively Exploited	❌ No known exploitation
Patch Status	See Vendor Advisory →
Reported By	CYBERDUDEBIVASH SENTINEL APEX Intelligence (via github_advisories)

🔬 Technical Analysis

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 `enable_message(..., use=False, handle=True)` only prevents the LLM from being instructed to generate the tool. The tool dispatch path in `agent_response()` → `handle_message()` → `get_tool_messages()` 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. ```python

from langroid.agent.chat_ag

📚 Advisory References

⚡ DETECTION RULES AVAILABLE

Get CVE-2026-54771 Detection Pack

Sigma rules, YARA signatures, IOC table, and SIEM queries for Splunk, Elastic, Sentinel, and Chronicle — deployable in 5 minutes.

✓ Sigma Rules ✓ YARA Pack ✓ IOC Table ✓ SIEM Queries

🛡️ Get Detection Pack → 🔌 Access via API →