UTC

AML.T0051.000

LLM Prompt Injection: Direct

An adversary may inject prompts directly as a user of the LLM. This type of injection may be used by the adversary to gain a foothold in the system or to misuse the LLM itself, as for example to generate harmful content.

  • Tactic Execution
  • Maturity: Realized
  • Generative AI
  • Agentic AI
Full entry on MITRE ATLAS →
Real cases on the map
  1. CriticalFlowise Prompt Injection to RCE and SSRF via CSV/Airtable Agent Python Validator Bypassflowise, flowise-components
  2. CriticalFlowise: CSV Agent Prompt Injection Remote Code Execution Vulnerabilityflowise, flowise-components
  3. CriticalFlowise: CSV Agent Prompt Injection Remote Code Execution Vulnerabilityflowise, flowise-components
  4. Criticalvanna vulnerable to remote code execution caused by prompt injectionvanna

Published advisories whose titles describe the ShieldMap technique this maps to.

Mitigations
  • AI Telemetry Logging and MonitoringAML.M0024

    Implement logging and monitoring across the AI lifecycle to detect suspicious activity and support investigation. Capture security-relevant access, changes, and operations across data pipelines, model development, deployment, and connected systems.

    Technical - Cyber

  • Input and Output Validation for AI Agent ComponentsAML.M0033

    Implement validation on inputs and outputs for the tools and data sources used by AI agents. Validation includes enforcing a common data format, schema validation, checks for sensitive or prohibited information leakage, and data sanitization to remove potential injections or unsafe code.

    Technical - AI

  • AI Red TeamAML.M0035

    Establish an AI red team responsible for conducting recurring, authorized, and threat-informed red-teaming exercises to identify and remediate vulnerabilities in AI-enabled systems before deployment and throughout operation.

    Policy · Technical - AI · Technical - Cyber

From MITRE ATLAS 2026.10, Copyright 2021-2026 MITRE, Apache License 2.0.