UTC

OWASP Top 10 for LLM Applications 2026

LLM04:2026 Supply Chain

5 advisories on ShieldMap fall under it through CWE-494, and 1 technique page explains how the attacks work.

OWASP Top 10 for Agentic Applications
  • ●ASI04:2026 Agentic Supply Chain VulnerabilitiesThis entry's own scope note defers agentic-specific supply-chain risk to ASI04, leaving this entry to cover the non-agentic model, dataset, and artifact supply chain
CWE weaknesses
  • ●CWE-494 Download of Code Without Integrity CheckModels and adapters are pulled by mutable tags or resolved by name without signature or hash verification, letting namespace reuse deliver code execution.
  • ●CWE-829 Inclusion of Functionality from Untrusted Control SphereThe entry centers on including third-party models, adapters, and packages from untrusted hubs and registries, including slopsquatting and tampered models.
  • ○CWE-349 Acceptance of Extraneous Untrusted Data With Trusted DataA malicious LoRA adapter merged into a trusted base model blends poisoned artifacts into an otherwise trusted merge-and-convert pipeline.
  • ○CWE-664 Improper Control of a Resource Through its LifetimeInsecure deserialization of model weights and native-parser memory corruption are lifetime-control failures over the loaded model resource.
MITRE ATLAS tactics
  • ●AML.TA0004 Initial AccessCompromised models, packages, adapters, and training pipelines are the foothold by which a tampered artifact enters the victim's environment.
  • ○AML.TA0003 Resource DevelopmentAttackers publish tampered models, pre-register confabulated (slopsquatted) package names, and re-register abandoned namespaces to stage malicious dependencies.
  • ○AML.TA0005 ExecutionMalicious model manifests, pickle deserialization, and format-parser overflows yield remote code execution when an artifact is loaded.
  • ○AML.TA0006 PersistenceA backdoor embedded in a LoRA adapter or a model's computational graph survives in the deployed model, in a format that looks safe.
NIST AI 600-1 risks
  • ●NIST Value Chain and Component IntegrationThe entry is entirely about the integrity of third-party models, datasets, adapters, and integrated components across the AI value chain.
  • ●NIST Information SecuritySupply-chain compromise produces backdoors, poisoning, remote code execution, and other security breaches.
  • ○NIST Intellectual PropertyUnclear licensing for use, distribution, and commercialization, plus copyright exposure from supplier material, put intellectual property at risk.
  • ○NIST Information IntegrityTampered or poisoned models emit biased outputs and misinformation, and a tampered on-device model can steer users to scam sites.
  • ○NIST ConfabulationCoding assistants confabulate nonexistent package names that attackers pre-register, the slopsquatting vector.
NIST AI RMF categories
  • ●GOVERN 6 third-party & supply-chain policyThe entire entry is LLM supply chain, covering supplier vetting, terms-and-conditions review, and component-patching policy for third-party software, data, and models.
  • ●MAP 4 map risks across all componentsA signed SBOM, AIBOM, and ML-SBOM component inventory together with component and supplier vetting maps risk across every third-party model, dataset, and dependency.
  • ●MANAGE 3 manage third-party risksVetting and re-auditing suppliers and treating model conversion or merge services as high-risk promotion points is direct third-party-entity risk management.
  • ○MEASURE 2 evaluate trustworthinessAI red teaming and evaluation when selecting third-party models, plus in-production adversarial-robustness testing and anomaly detection, assess acquired components.
  • ○MEASURE 3 track risks over timeContinuous validation of upstream model integrity, in-production anomaly detection, and regular BOM and supplier re-audits track supply-chain risk over time.
OWASP GenAI Data Security
  • ●DSGAI04 Data, Model & Artifact PoisoningTampered or backdoored models, adapters, and artifacts enter the pipeline through the supply chain, as with a maliciously edited open model or a poisoned format-conversion service.
  • ●DSGAI05 Data Integrity & Validation FailuresUnsigned, unverified artifacts and mutable references resolved at build or promotion time let tampered components pass without integrity checks or signing.
  • ○DSGAI03 Shadow AI & Unsanctioned Data FlowsUnclear supplier terms can silently route application data into a provider's training set, so vetting supplier terms and privacy policies is required.
  • ○DSGAI08 Non-Compliance & Regulatory ViolationsUnclear model and dataset licensing and copyright status create legal and compliance exposure that demands license tracking and auditing.
OWASP AIVSS agentic risks
  • ○AIVSS-8 Agent Supply Chain and Dependency RiskCompromised third-party packages, pre-trained models, LoRA adapters, and conversion or merge pipelines are the dependency substrate an agent inherits, so a tampered model-supply-chain artifact becomes the agent's supply chain too.
CSA AI Controls Matrix domains
  • ●STA Supply Chain Management, Transparency, and Accountability
  • ●MDS Model Development Security
  • ○TVM Threat & Vulnerability Management
  • ○CEK Cryptography, Encryption & Key Management
  • ○CCC Change Control and Configuration 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.