Techniques › T1699
T1699 Direct Prompt Injection
execution — Windows, SaaS · attack.mitre.org · JSON
0
MITRE detection strategies
0
analytics
0
Sigma rules tagged attack.t1699
0
KEV CVEs mapped here
<p>Adversaries may input malicious prompts directly into an LLM’s user interface. The prompts can be designed to bypass safeguards, manipulate context, override previous instructions, or coerce the LLM into unauthorized behavior.</p><p>Adversaries may use direct prompt injection to Generate Content prohibited by the LLM's guardrails or to induce the system to utilize its capabilities in unintended or prohibited ways. Adversaries may achieve this by instructing the LLM to ignore previous instructions or safety rules, or by impersonating a role such as a researcher or privileged user.</p>
KEV CVEs mapped to this technique · CTID Mappings Explorer
None. No KEV entry in the public mapping names this technique. Given that 75.7% of KEV has no mapping at all, this says more about the mapping than about the technique.
Detection strategy · ATT&CK Enterprise v20.0
MITRE publishes no detection strategy for this technique in v20.0.
Sigma rules · SigmaHQ c04ad420b4, tag attack.t1699
No Sigma rule carries this tag.