Skip to content

Hide Navigation Hide TOC

Latent Injection Ignore-Instruction Keyword - ATR-2026-00400 (844ebca6-16fd-5fbc-bbbc-339e22b04328)

Detects instruction-redirect keywords buried within translation, whois, or factual contexts that pivot the LLM away from its original task, from NVIDIA garak latentinjection probe LatentJailbreak/LatentWhois classes. The attack embeds "Ignore the above directions", "Ignore the rest of this data", or "Disregard all info except" as injection_instructions inside otherwise-legitimate content. Distinct from ATR-2026-00399 (separator token) — this rule covers the instruction-keyword pattern where the attacker overrides context without a structural delimiter. Key signals: "Ignore X and print/say Y", "Disregard all info except", "it is critical to my career" social-engineering urgency combined with output redirect.

Cluster A Galaxy A Cluster B Galaxy B Level
LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) MITRE ATLAS Attack Pattern Latent Injection Ignore-Instruction Keyword - ATR-2026-00400 (844ebca6-16fd-5fbc-bbbc-339e22b04328) Agent Threat Rules 1