AI / ML CVE-2026-21521
HIGHAttack ChainAIDerived
Hypothetical attack flow derived from CVE metadata – not a confirmed exploit chain
-
AccessCraft malicious input with control sequences
-
DeliveryUser clicks/interacts with crafted content
-
ExploitCopilot fails to neutralize escape sequences
-
ExecutionInformation disclosure occurs
-
ImpactAttacker retrieves sensitive data
Vulnerability Assessment
| Weakness |
CWE
OWASP Top 10:2025
A05:2025 - Injection
ASVS 5.0
V1 - Encoding and Sanitization Escape character neutralization
|
| Exploitation Conditions | User interaction required (UI:R). Target must be running vulnerable Copilot version. Attacker crafts input containing improperly neutralized escape or control sequences. No authentication required; remote exploitation possible via network vector. |
| Impact | CVSS 7.4 (HIGH). Attack vector: Network. Complexity: Low. Privileges required: None. User interaction: Required. Exploitation no authentication required. Exploitable via remote/network. |
| Exploit ScenarioDerived | A remote attacker without authentication could exploit this vulnerability to compromise the affected system. |
Get an e-mail when this CVE is exploited, patched or re-scored. Free account.
Alert meAnalysisAIv1 – Mar 12, 2026
Information disclosure in Microsoft 365 Word Copilot enables unauthenticated attackers to extract sensitive data through improper handling of escape and control sequences in network communications. The vulnerability requires user interaction to trigger and affects the Copilot AI/ML service with a CVSS score of 7.4. No patch is currently available.
Earlier versions of this analysis (1)
Improper neutralization of escape, meta, or control sequences in Copilot allows an unauthorized attacker to disclose information over a network. [CVSS 7.4 HIGH]
RemediationAI
Monitor vendor advisories for a patch. Restrict network access to the affected service where possible.
Affected Packages
Source: OSV (Open Source Vulnerabilities)
Affects your stack
Affects 1 package in microsoft
Checking this CVE against your own stacks and servers is part of the Basic plan and up.
Technical ContextAI · show details
Affects 365 Word Copilot. Improper neutralization of escape, meta, or control sequences in Copilot allows an unauthorized attacker to disclose information over a network.
Know when AI / ML gets its next vulnerability
- Watch products and get an email when something new is published
- Check this CVE against your own stack and servers
- Exploit and PoC references, threat intelligence from 22 sources
No credit card · 7-day full trial
Severity by source
AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:N/A:N
Primary rating from NVD · only source for this CVE.
CVSS VectorNVD
DescriptionCVE.org
Improper neutralization of escape, meta, or control sequences in Copilot allows an unauthorized attacker to disclose information over a network.
Executive ViewAI
CVE-2026-21521 is a high-severity vulnerability in Copilot that enables attackers to extract sensitive information through improper handling of control sequences. With no patch currently available, organizations using Copilot face immediate risk of data disclosure until vendor remediation is released.
Implement network segmentation isolating Copilot from sensitive data systems; restrict outbound network connectivity to approved endpoints only; disable Copilot functionality if business-critical operations do not depend on it; deploy WAF/proxy rules to monitor and block suspicious control sequences in Copilot traffic; enforce strict access controls limiting which users/services interact with Copilot; increase logging and monitoring for unusual data exfiltration patterns; consider temporary suspension of Copilot use for processing confidential or regulated data.
Threat Intelligence Overview
How this decision was reached
The engine reads each signal below and applies a fixed list of rules from top to bottom. The first rule that matches sets the recommended action – like a statement, every line is shown.
What every action level means
SSVC AssessmentENISA
Priority Score
Attack Technique
Information disclosure occurs when an application unintentionally exposes sensitive data that aids attackers in reconnaissance or directly compromises security.
Affected Products (CPE)CVE.org
MCPJam Inspector versions 1.4.2 and earlier allow unauthenticated remote code execution through missing authentication i
Langflow has a code injection vulnerability in the code component (EPSS 2.6%) enabling remote code execution through the
Langflow has an eval injection in eval_custom_component_code (EPSS 2.0%) enabling remote code execution through crafted
A path traversal vulnerability exists in mlflow/mlflow version 2.15.1. Rated high severity (CVSS 7.5), this vulnerabilit
Code injection in Langflow CSV Agent node before 1.8.0. The node hardcodes allow_dangerous_code=True, enabling arbitrary
Sandbox escape in Enclave JavaScript sandbox before 2.11.1. Enclave is designed for safe AI agent code execution — the e
enclave-vm JavaScript sandbox (before 2.7.0) has a critical sandbox escape. When a tool invocation fails, a host-side Er
A remote code execution vulnerability in langchain-ai/langchain (CVSS 10.0). Risk factors: public PoC available. Vendor
n8n has a fifth critical RCE vulnerability (CVSS 9.9) in the Expression evaluator, enabling code execution through craft
Path traversal vulnerability in RAGFlow RAG engine version 0.23.1 allows unauthenticated attackers to read arbitrary fil
WeKnora LLM framework (before 0.2.5) allows authenticated users to inject MCP stdio commands that the server executes as
OS command injection in WeKnora from version 0.2.5 allows authenticated users to execute arbitrary system commands. CVSS
NVD
CVE.org
EPSS
GitHub PoC
Exploit-DB