UTC

OWASP Top 10 for LLM Applications 2026

LLM06:2026 Unbounded Consumption

152 advisories on ShieldMap fall under it through CWE-400, CWE-770, and 1 technique page explains how the attacks work.

OWASP Top 10 for Agentic Applications
  • ●ASI02:2026 Tool Misuse & ExploitationAgent-tool interaction loops and MCP tool-call fan-out let a single request drive recursive or high-volume tool calls that exhaust budget and availability
  • ●ASI08:2026 Cascading FailuresAgentic architectures and tool-use protocols such as MCP "amplify a single request into cascading downstream operations," illustrated by the fan-out of one task into 50 calls
CWE weaknesses
  • ●CWE-400 Uncontrolled Resource ConsumptionEvery input-flood, context-overflow, thinking-token, and GPU-or-memory exhaustion pattern in the entry is a form of uncontrolled resource consumption.
  • ●CWE-770 Allocation of Resources Without Limits or ThrottlingThe defining root cause is the absence of rate, token, cost, and queue limits, with pre-flight estimation and hard spending caps as the missing controls.
  • ○CWE-664 Improper Control of a Resource Through its LifetimeThe pillar ancestor of the consumption weaknesses covers management of the compute and memory resource across its lifetime.
  • ○CWE-691 Insufficient Control Flow ManagementReasoning loops that burn thinking tokens and recursive or infinite tool-calling loops need recursion-depth limits and loop detection.
  • ○CWE-829 Inclusion of Functionality from Untrusted Control SphereA malicious third-party tool or skill pulled from an open-source repository drives the resource-exhausting loops.
MITRE ATLAS tactics
  • ●AML.TA0011 ImpactInput floods deny the ML service to legitimate users, and cost-harvesting attacks run up the victim's bill in a denial-of-wallet.
  • ●AML.TA0010 ExfiltrationCrafted API queries and side-channel weight harvesting extract the model, stealing the intellectual property embodied in its parameters.
  • ○AML.TA0000 AI Model AccessBoth extraction and resource-exhaustion attacks operate through inference-API access, which is the prerequisite for the technique.
NIST AI 600-1 risks
  • ●NIST Information SecurityUnbounded consumption threatens availability through denial of service and confidentiality through model extraction and side-channel theft of weights and architecture.
  • ○NIST Intellectual PropertyModel extraction and functional cloning steal the model as intellectual property and trade secret.
  • ○NIST Value Chain and Component IntegrationShared inference infrastructure and third-party serving frameworks add supply-chain attack surface.
NIST AI RMF categories
  • ○MANAGE 1 prioritize & respond to risksRate limits, hard spending caps, agentic circuit breakers, and graceful degradation form an impact-prioritized response informed by cost-attribution monitoring and baselines.
  • ○MEASURE 2 evaluate trustworthinessAdversarial-perturbation scanning and resource-consumption red-teaming, supported by tool-behavior baselines, evaluate the system for the secure-and-resilient availability characteristic.
OWASP GenAI Data Security
  • ●DSGAI20 Model Exfiltration & IP ReplicationFunctional model cloning and extraction through high-volume querying steal the model's intellectual property.
  • ●DSGAI17 Data Availability & Resilience Failures in AI PipelinesResource-exhausting requests and output-explosion attacks render the service unresponsive, the availability failure that resilience controls target.
  • ○DSGAI04 Data, Model & Artifact PoisoningA single poisoned fine-tuning sample can break end-of-sequence behavior and drive runaway output generation as a denial-of-service vector.
OWASP AIVSS agentic risks
  • ○AIVSS-1 Agentic AI Tool MisuseA malicious tool forces an agent into recursive or infinite tool-calling loops, driving token consumption and cost far beyond the task's needs.
  • ○AIVSS-3 Agent Cascading FailuresAgentic and MCP protocols amplify a single request into cascading downstream operations, so one task fans out into many tool calls that exhaust budget and availability.
  • ○AIVSS-8 Agent Supply Chain and Dependency RiskAn attacker publishes a malicious tool, such as a skill on an open-source repository, that developers incorporate as an agent dependency, driving token exhaustion once integrated.
CSA AI Controls Matrix domains
  • ●AIS Application & Interface Security
  • ●BCR Business Continuity Management and Operational Resilience
  • ○IVS Infrastructure & Virtualization Security
  • ○LOG Logging and Monitoring
  • ○IAM Identity & Access Management

Mappings and their reasons from the OWASP Top 10 for LLM Applications 2026, Appendix A (OWASP GenAI Security Project), shared under CC BY-SA 4.0. Mappings restructured as data; the ATT&CK section and the AICM relevance text left out. Navigation, not a compliance claim.