Explore 1 source-supported AI security cases for AML.T0018.003 · Modify Prompt Construction Logic in MITRE ATLAS, with evidence, scope, and defensive analysis.
Risk category
Adversaries may modify templates, role delimiters, embedded system instructions, tokenizer settings, tool-call formatting, or other artifact-bundled logic that constructs the context sent to an AI model. Model file formats such as GGUF can package this logic alongside model weights in a single distributable artifact. A compatible inference runtime may interpret the modified logic during future inference requests, enabling persistent covert instruction injection, altered instruction precedence, redirected tool use, or manipulated model output without changing model weights.
Researchers from Pillar Security and Fujitsu showed that a GGUF artifact can carry a modified Jinja chat template while its model weights remain unchanged. When a trigger appears, the inference engine renders attacker instructions into system-level context before the model runs; controlled tests degraded model behavior and hijacked BrowserUse and OpenHands tool use. Defenders need to treat chat templates as executable release artifacts, verify their exact bytes and provenance, regression-test every conversion, and enforce tool and data-flow boundaries.
ATLAS annotations follow the source SecureFlow steps; they are not a MITRE endorsement of cross-framework mappings.