Skip to content

Hide Navigation Hide TOC

Indirect Prompt Injection via Tool Responses - ATR-2026-00083 (e20353f8-0ece-5104-9530-ab59dea5ef8d)

Detects indirect prompt injection payloads embedded in tool responses, API outputs, or retrieved content. Attackers place hidden instructions in external data sources that the agent processes, causing it to execute unintended actions when the poisoned data is consumed.

Cluster A Galaxy A Cluster B Galaxy B Level
LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) MITRE ATLAS Attack Pattern Indirect Prompt Injection via Tool Responses - ATR-2026-00083 (e20353f8-0ece-5104-9530-ab59dea5ef8d) Agent Threat Rules 1