UTC

AML.T0051.002

LLM Prompt Injection: Triggered

An adversary may trigger a prompt injection via a user action or event that occurs within the victim's environment. Triggered prompt injections often target AI agents, which can be activated by means the adversary identifies during Discovery (See Activation Triggers).

  • Tactic Execution
  • Maturity: Demonstrated
  • 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.