MITRE ATLAS 2026.09 / technique reference

AML.T0051.001
Indirect

← Back to the ATLAS matrix · Pinned MITRE source · Current MITRE ATLAS site

Generative AIAgentic AIExecutionSource maturity: Demonstrated

MITRE source definition

An adversary may inject prompts indirectly via a separate data channel that the LLM or AI agent ingests, such as text or multimedia pulled from documents, emails, databases or websites. These instructions originate from adversary-controlled content rather than the legitimate user, and are frequently hidden or obfuscated (See LLM Prompt Obfuscation) from the user, for example as invisible text.

Adversaries may use this to hijack an agent or LLM in order to gain a foothold in the target system or to act against an unwitting user of that system, inheriting whatever privileges the AI system holds. Adversaries may also stage the lure that causes the content to be reached (See AI Agent Clickbait), or use the resulting foothold to establish persistence (See AI Agent Context Poisoning).

Indirect prompt injections have been observed in the wild, with potential impact ranging from harmless pranks, to search engine optimization manipulation, data exfiltration, and destructive actions.[[google-prompt-injections-web]]

Source modified 2026-09-15. Reproduced from the pinned ATLAS release; inline technique links resolve to local reference pages.

Source-backed defensive context

MITRE mitigations

MITRE case studies

These are explicit source relationships, not independently reproduced incidents or validated detection coverage. The local relationship indexes link back to the pinned MITRE source.

Detection and collection design

No executable detector is supplied by this ATLAS source import. Define detection against the specific behavior in the full definition above. MITRE case-study and mitigation relationships supply context, not tested rule coverage.

MITRE explicitly links AI Telemetry Logging to this technique. Use that guidance to identify system-appropriate records.

Depending on the selected scenario, the experiment may need dataset/model versions, data-access and build audit records, inference or application traces, or agent tool authorization records. These are planning options, not asserted mappings. Minimize sensitive prompt/data capture and retain provenance.

Anomaly detection design

No exact ATLAS anomaly detector is validated here. Select a measurable feature from the behavior definition; compare like-for-like model versions, workloads and identities. Changes caused by model upgrades, retrieval corpora or legitimate workload shifts must be controls, not automatically labelled attacks.

Baseline and validation methodology · AI-security ecosystem

Tools and reproducible source scenarios

No lab-tool association is invented from the technique name. Inspect the exact source scenarios below for the tools and environment actually used; a case study is not itself an executable or safe lab.

Simulation experiment plan

Select an owned, disposable system implementing AML.T0051.001 Indirect. Use synthetic data and sandboxed tools; disable production credentials, external side effects and data exfiltration. For poisoning or supply-chain tests, use throwaway artifacts rather than real training or deployment pipelines.

  1. State the exact trust boundary and expected observable behavior.
  2. Pin model, application, dataset, tool permissions and evaluation inputs.
  3. Capture baseline and scenario traces, an authorized look-alike, and a missing-telemetry control.
  4. Evaluate the detector against independently labelled results; do not substitute model output claims for observed tool actions.
  5. Restore state and preserve redacted evidence.

Experiment worksheet — not fabricated telemetry

The export below is a planning record, not a native event, positive attack fixture or execution result. Unknown fields deliberately remain null.

{
  "schema": "1200km.atlas.experiment-plan.v1",
  "technique_id": "AML.T0051.001",
  "simulation": false,
  "target": "REQUIRES_OWNED_LAB",
  "source_scenario": [
    "AML.CS0020",
    "AML.CS0021",
    "AML.CS0026",
    "AML.CS0029",
    "AML.CS0035",
    "AML.CS0038",
    "AML.CS0039",
    "AML.CS0040",
    "AML.CS0045",
    "AML.CS0046",
    "AML.CS0048",
    "AML.CS0049",
    "AML.CS0051",
    "AML.CS0054",
    "AML.CS0055",
    "AML.CS0063",
    "AML.CS0066",
    "AML.CS0067"
  ],
  "input_artifact_hash": null,
  "system_version": null,
  "expected_observable": null,
  "native_telemetry_location": null,
  "baseline_reference": null,
  "result": "not_run"
}

Simulation and telemetry boundary

This is a technique reference page, not a runnable simulation. No ATLAS-specific telemetry mapping, local attack execution or detector validation is asserted. MITRE maturity describes its source evidence, not a 1200km lab result.

For broader context—not technique-specific control mappings—see AI Security, AI Security Course, and detection-validation methodology.

Provenance and attribution

Immutable MITRE ATLAS source · Import provenance · Attribution and transformation notice · Apache License 2.0

Copyright 2021-2026 MITRE. Source text and explicit relationships are retained; navigation, formatting and local links are provided by 1200km.