AML.T0048.003
User Harm

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.

No explicit AI Telemetry Logging mitigation relationship was found for this technique. Do not manufacture a sensor mapping from its tactic.

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.

• AML.CS0020 Indirect Prompt Injection Threats: Bing Chat Data Pirate (Exercise)
• AML.CS0021 ChatGPT Conversation Exfiltration (Exercise)
• AML.CS0022 ChatGPT Package Hallucination (Exercise)
• AML.CS0024 Morris II Worm: RAG-Based Attack (Exercise)
• AML.CS0029 Google Bard Conversation Exfiltration (Exercise)
• AML.CS0032 Attempted Evasion of ML Phishing Webpage Detection System (Incident)
• AML.CS0036 AIKatz: Attacking LLM Desktop Applications (Exercise)
• AML.CS0040 Hacking ChatGPT's Memories with Prompt Injection (Exercise)
• AML.CS0041 Rules File Backdoor: Supply Chain Attack on AI Coding Assistants (Exercise)
• AML.CS0048 Exposed ClawdBot Control Interfaces Leads to Credential Access and Execution (Exercise)
• AML.CS0054 Data Exfiltration via Remote Poisoned MCP Tool (Exercise)
• AML.CS0056 Model Distillation Campaigns Targeting Anthropic Claude (Incident)
• AML.CS0063 Prompt-Based Attacks Against Gemini via Calendar Invitations (Exercise)
• AML.CS0064 Poisoned GGUF Templates: Inference-Time Supply Chain Attack (Exercise)

Simulation experiment plan

Select an owned, disposable system implementing AML.T0048.003 User Harm. 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.T0048.003",
  "simulation": false,
  "target": "REQUIRES_OWNED_LAB",
  "source_scenario": [
    "AML.CS0020",
    "AML.CS0021",
    "AML.CS0022",
    "AML.CS0024",
    "AML.CS0029",
    "AML.CS0032",
    "AML.CS0036",
    "AML.CS0040",
    "AML.CS0041",
    "AML.CS0048",
    "AML.CS0054",
    "AML.CS0056",
    "AML.CS0063",
    "AML.CS0064"
  ],
  "input_artifact_hash": null,
  "system_version": null,
  "expected_observable": null,
  "native_telemetry_location": null,
  "baseline_reference": null,
  "result": "not_run"
}