Skip to content

Hide Navigation Hide TOC

Indirect PI — Account Manipulation / Emergency Service Dispatch via Pretext - ATR-2026-00722 (2bd566ea-aeed-5c9a-8f88-226d87f1b79a)

Detects indirect prompt injection payloads that instruct an agent to perform account manipulation using fabricated emergency pretexts: dispatching fire/ police response to specific addresses, triggering emergency services, or modifying account security policies using false emergency claims. The payload is embedded in consumed structured data and exploits agents with emergency dispatch or account management tool access. Source: indirect-pi-account-manipulation-carrier / indirect-pi-infrastructure-carrier.

Cluster A Galaxy A Cluster B Galaxy B Level
Indirect (a4a55526-2f1f-403b-9691-609e46381e17) MITRE ATLAS Attack Pattern Indirect PI — Account Manipulation / Emergency Service Dispatch via Pretext - ATR-2026-00722 (2bd566ea-aeed-5c9a-8f88-226d87f1b79a) Agent Threat Rules 1
LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) MITRE ATLAS Attack Pattern Indirect PI — Account Manipulation / Emergency Service Dispatch via Pretext - ATR-2026-00722 (2bd566ea-aeed-5c9a-8f88-226d87f1b79a) Agent Threat Rules 1
Indirect (a4a55526-2f1f-403b-9691-609e46381e17) MITRE ATLAS Attack Pattern LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) MITRE ATLAS Attack Pattern 2