AML.T0068: LLM Prompt Obfuscation
Adversaries may hide or otherwise obfuscate prompt injections or retrieval content to avoid detection from humans, large language model (LLM) guardrails, or other detection mechanisms.
For text inputs, this may include modifying how the instructions are rendered such as small text, text colored the same as the background, or hidden HTML elements. For multi-modal inputs, malicious instructions could be hidden in the data itself (e.g. in the pixels of an image) or in file metadata (e.g. EXIF for images, ID3 tags for audio, or document metadata).
Inputs can also be obscured via an encoding scheme such as base64 or rot13. This may bypass LLM guardrails that identify malicious content and may not be as easily identifiable as malicious to a human in the loop.
Standards mapping
Where this fits in a TurboPentest engagement
TurboPentest's agentic pentest is powerful and covers a broad range of issues automatically. This particular class is best confirmed in a manual IntegSec engagement, where human pentesters apply deeper methodology and a larger context window than any automated pass.
Frequently asked questions
What is AML.T0068 LLM Prompt Obfuscation?
Adversaries may hide or otherwise obfuscate prompt injections or retrieval content to avoid detection from humans, large language model (LLM) guardrails, or other detection mechanisms. For text inputs, this may include modifying how the instructions are rendered such as small text, text colored the same as the background, or hidden HTML elements. For multi-modal inputs, malicious instructions could be hidden in the data itself (e.g. in the pixels of an image) or in file metadata (e.g. EXIF for images, ID3 tags for audio, or document metadata). Inputs can also be obscured via an encoding scheme such as base64 or rot13. This may bypass LLM guardrails that identify malicious content and may not be as easily identifiable as malicious to a human in the loop.
Which tactics does AML.T0068 belong to?
AML.T0068 maps to the Defense Evasion tactic.
Does TurboPentest test for LLM Prompt Obfuscation?
TurboPentest's agentic pentest is powerful and covers a broad range of issues automatically. This particular class is best confirmed in a manual IntegSec engagement, where human pentesters apply deeper methodology and a larger context window than any automated pass.
Related MITRE ATLAS techniques
- Initial Access, Defense Evasion, ImpactAML.T0015: Evade AI Model
- Privilege Escalation, Defense EvasionAML.T0054: LLM Jailbreak
- Defense EvasionAML.T0067: LLM Trusted Output Components Manipulation
- Defense EvasionAML.T0071: False RAG Entry Injection
- Defense EvasionAML.T0073: Impersonation
- Defense EvasionAML.T0074: Masquerading
Find these issues before an attacker does
TurboPentest runs an agentic AI pentest against your target and reports findings with proof, from $99 per target.
Start a $99 pentest