LLM Prompt Injection AML.T0051
An adversary may craft malicious prompts as inputs to an LLM that cause the LLM to act in unintended ways. These "prompt injections" are often designed to cause the model to ignore aspects of its original instructions and follow the adversary's instructions instead.
MITRE ATLAS technique. Tactics: Execution. View on atlas.mitre.org
Rules tagged with this technique
Every catalog rule tagged with this ATLAS technique, grouped by vendor. Click a rule title for its full predicates, exclusions, and indicators.
Elastic 7 rules
- AWS Bedrock Guardrails Detected Multiple Policy Violations Within a Single Blocked Request
- AWS Bedrock Guardrails Detected Multiple Violations by a Single User Over a Session
- AWS Bedrock Invocations without Guardrails Detected by a Single User Over a Session
- Unusual High Confidence Content Filter Blocks Detected
- Unusual High Denied Sensitive Information Policy Blocks Detected
- Unusual High Denied Topic Blocks Detected
- Unusual High Word Policy Blocks Detected