H3XAOperational intelligence
Live analytical pictureEvidence before assessment
Threat intelligence / Technique

System Prompt

Adversaries may discover a large language model's system instructions provided by the AI system builder to learn about the system's capabilities and circumvent its guardrails.

Technique
TypeTechnique
External ID—
First seen2026-08-14
Last seen2026-08-14

Confidence

—

Adversaries may discover a large language model's system instructions provided by the AI system builder to learn about the system's capabilities and circumvent its guardrails.

5 recorded

Relationships

mitigates
from Control Access to AI Models and Data at Rest
Mitigation
mitigates
from Control Access to AI Models and Data in Production
Mitigation
mitigates
from Generative AI Guardrails
Mitigation
subtechnique-of
to Discover LLM System Information
Technique
uses
from Exposed ClawdBot Control Interfaces Leads to Credential Access and Execution
Campaign
1 external

References

mitre-atlas
AML.T0069.002
open
Continue into the dataIntelligence explorerHow to read the graphEvidence & provenance