Skip to content

Hide Navigation Hide TOC

Delimiter-Fence Ignore-Instructions Override - ATR-2026-02013 (17398814-d654-505d-b2c6-bef0618827c9)

Detects prompt injection payloads that wrap a fake "instruction block" inside a triple-quote delimiter fence and pair it with an ignore/disregard directive targeting surrounding instructions, prompts, or text -- the classic HackAPrompt payload-splitting jailbreak structure. Attackers use the delimiter fence to visually mimic a system or document boundary, then place an ignore-instructions directive inside or immediately around it to override the actual task and force an attacker-chosen output (often a fixed string assembled via variable substitution or character concatenation). Recovered from the HackAPrompt false-negative corpus, where this fenced variant evaded the existing plain-text "ignore instructions" rule family.

Cluster A Galaxy A Cluster B Galaxy B Level
LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) MITRE ATLAS Attack Pattern Delimiter-Fence Ignore-Instructions Override - ATR-2026-02013 (17398814-d654-505d-b2c6-bef0618827c9) Agent Threat Rules 1
Delimiter-Fence Ignore-Instructions Override - ATR-2026-02013 (17398814-d654-505d-b2c6-bef0618827c9) Agent Threat Rules LLM Jailbreak (172427e3-9ecc-49a3-b628-96b824cc4131) MITRE ATLAS Attack Pattern 1
Delimiter-Fence Ignore-Instructions Override - ATR-2026-02013 (17398814-d654-505d-b2c6-bef0618827c9) Agent Threat Rules Impair Defenses - T1562 (3d333250-30e4-4a82-9edc-756c68afc529) Attack Pattern 1
Disable or Modify Tools - T1685 (bbde9781-60aa-4b8a-a911-895b0c1b3872) Attack Pattern Impair Defenses - T1562 (3d333250-30e4-4a82-9edc-756c68afc529) Attack Pattern 2