UTC

AML.CS0035

Data Exfiltration from Slack AI via Indirect Prompt Injection

Type
Exercise
When
2024-08-20
Actor, as ATLAS names it
Not stated
Target
Slack AI
  • ATLAS attributes it to PromptArmor (security evaluation).
Techniques, in order
  1. 1Retrieval Content CraftingAI Attack Adaptation · AML.T0066
  2. 2LLM Prompt CraftingAI Attack Adaptation · AML.T0065
  3. 3Valid AccountsInitial Access · AML.T0012
  4. 4AI-Enabled Product or ServiceAI Model Access · AML.T0047
  5. 5RAG PoisoningPersistence · AML.T0070
  6. 6LLM Prompt Injection: IndirectExecution · AML.T0051.001
  7. 7RAG Credential HarvestingCredential Access · AML.T0082
  8. 8LLM Response RenderingExfiltration · AML.T0077
The full case study on MITRE ATLAS →

From MITRE ATLAS 2026.10 (Apache-2.0). ShieldMap lists who and what was involved and the techniques used, and links to ATLAS for the write-up; it does not copy the steps. Attribution is ATLAS's, not ShieldPi's.