OWASP LLM
LLM10 · Unbounded Consumption
Uncontrolled inference usage causes denial of service, runaway costs (denial of wallet) or model extraction.
OWASP Top 10 for LLM Applications (2025)
Mitigations
- Quotas, rate limits and budget alerts
- Detect scripted extraction patterns
- Protect API keys (LLMjacking)
Detections 12
- Bedrock model-access enablement APIs called with a long-term access key
- Bedrock model invocation logging configuration deleted
- Bedrock invocation probing: failed model calls across models or regions
- Bedrock reconnaissance burst: model, availability and logging checks in one hour
- Bedrock calls from a long-term access key with a browser, empty or scripting user agent
- Bedrock invocation volume far above a principal's own baseline
- One source IP using several AWS principals against Bedrock
- Azure OpenAI / AI Foundry account keys listed by a new caller
- Azure OpenAI model deployment or Responsible AI policy changed
- Azure OpenAI data-plane requests from a caller IP not seen in the previous two weeks
Related techniques
- AML.T0034 Cost Harvesting MITRE ATLAS
In the news
No stories mapped to this technique yet.
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.