llmthreat
For vendors27 vendors · 15 toolsMatrixVendors
OWASP LLM Top 10 · LLM04

Which LLM-security vendors cover LLM04 Supply Chain? (2026)

LLM04 Supply Chain — Compromised models, datasets, plugins, or dependencies add risk before runtime. As of , 7 of 27 vendors llmthreat tracks score Covered for this risk, 17 more score Partial. Scores are llmthreat's editorial read of public documentation, not a third-party audit.

7/27
Covered
17
Partial
2
Not covered
1
Unverified

How it happens

LLM apps pull in pretrained models, LoRA/PEFT adapters, datasets, and tooling from third parties, and any of those can be tampered with before you ever load them. Real incidents: JFrog found roughly 100 malicious models on Hugging Face using unsafe pickle deserialization to run arbitrary code on load; the Ultralytics YOLO PyPI package was compromised in December 2024 (versions 8.3.41/8.3.42 shipped a cryptominer) showing the same pattern hits ML tooling, not just model weights. A backdoored LoRA adapter can behave normally until a specific trigger phrase flips its output — hard to catch by just eyeballing benchmark scores.

How to test for it

Run ModelScan (Protect AI, open source) against any pickle/H5/SavedModel file before it touches production — it flags unsafe deserialization code embedded in the file. Prefer safetensors over pickle where the model source supports it, since safetensors can't execute code on load. Run standard SCA tools (Snyk, OSV-Scanner) against your ML dependency tree the same way you would any other package, and maintain an AI-BOM (CycloneDX ML-BOM) so you can tell what's actually in your pipeline when a CVE or compromised-package advisory drops.

How to mitigate it

Pull models and adapters only from sources you can verify (signed commits, publisher checksums), scan every model file with ModelScan or equivalent in CI before deployment, and pin + hash-check package versions rather than trusting "latest." Re-scan on every model or dependency upgrade — a clean model today doesn't mean the next version is clean. This doesn't catch a backdoor baked into weights that pass a functional scan; that requires the poisoning-specific testing under LLM05.

Which vendors cover LLM04 Supply Chain?

Vendors covering LLM04 Supply Chain — as of 2026-10-30
VendorCategoryCoverageHow it's addressedSource
Noma SecurityAI-SPM / Runtime ProtectionCoveredIdentifies/remediates AI supply-chain risk: vulnerable data pipelines, misconfigured MLOps, malicious models.https://techcrunch.com/2024/10/31/noma-is-building-tools-to-spot-security-issues-with-ai-apps/
Pillar SecurityAI-SPM / Runtime ProtectionCoveredAI Discovery & Posture traces dependency chains, validates model provenance, and stops unapproved models from deploying.https://www.pillar.security/platform/ai-discovery-posture
HiddenLayerAI-SPM / Runtime ProtectionCoveredModel Scanner scans for malicious models, backdoored weights and vulnerable dependencies before deployment.https://hiddenlayer.com/model-scanner/
Protect AIAI-SPM / Runtime ProtectionCoveredGuardian scans 35+ model formats and 1.5M+ Hugging Face models; huntr AI/ML bug bounty.https://web.archive.org/web/20260319043333/https://protectai.com/guardian
ApiiroAI-SPM / Runtime ProtectionCoveredSoftware supply-chain security, SCA/SBOM and malicious-code detection are core strengths.https://apiiro.com/
CraniumAI-SPM / Runtime ProtectionCoveredSystem-of-record for models, data, infra and vendors; third-party AI monitoring (AIBOM-style supply-chain inventory).https://cranium.ai/
Credo AIAI Governance / Model RiskCoveredAI Registry catalogs vendors/models with dependency mapping; vendor/third-party AI risk management.https://www.credo.ai/
LakeraGuardrails / LLM FirewallPartialVendor marks supply chain as outside runtime scope; Lakera Red offers limited behavior evaluation.https://www.lakera.ai/blog/owasp-top-10-for-llm-applications-lakera-alignment
NeuralTrustGuardrails / LLM FirewallPartialFree MCP Scanner identifies vulnerabilities and misconfigurations (tool poisoning, RCE-chaining, data exfiltration) in MCP server setups — a narrow supply-chain-adjacent surface, not comprehensive model/dependency supply-chain scanning.https://neuraltrust.ai/mcp-scanner
VijilAgentic AI SecurityPartialDepot provides hardened LLMs, reducing base-model provenance risk; broader supply-chain scanning not detailed.https://vijil.ai/
Enkrypt AIGuardrails / LLM FirewallPartialMCP Scanner/Gateway secures Model Context Protocol; not full model-artifact supply-chain scanning.https://www.enkryptai.com/
Operant AIAI-SPM / Runtime ProtectionPartialCodeInjectionGuard intercepts agent-initiated package installs, but no model-file or dataset provenance scanning is documented.https://www.operant.ai/solutions/code-agents
Robust IntelligenceAI Red TeamingPartialModel validation scans models before deployment; supply-chain aspects partial.https://sequoiacap.com/article/robust-intelligence-spotlight/
StraikerAgentic AI SecurityPartialDiscover AI maps MCP servers and flags dangerous/misconfigured MCP tools; not model-file supply-chain scanning.https://www.straiker.ai/
ZenityAgentic AI SecurityPartialAISPM inventories and risk-scores third-party AI integrations and discovers MCP servers, which Zenity labels posture only.https://zenity.io/blog/how-zenity-implements-the-owasp-top-10-for-llm-applications
AktoAgentic AI SecurityPartialLists supply-chain vulnerabilities among covered attack surface.https://www.akto.io/agentic-security
AurascapeGuardrails / LLM FirewallPartialCoding Assistant Guardrails stop typosquatted and poisoned packages, but no model-file or dataset provenance control is documented.https://aurascape.ai/coding-assistant-guardrails/
Lasso SecurityGuardrails / LLM FirewallPartialAgent hardening includes mitigating supply-chain risks and misconfigurations.https://www.lasso.security/blog/owasp-ai-red-teaming-landscape
MindgardAI Red TeamingPartialDiscover produces AI-BOM and surfaces shadow AI; not full dependency supply-chain scanning.https://mindgard.ai/
TrojAIAI Red TeamingPartialJFrog DevSecOps integration scans models in the pipeline/supply chain.https://troj.ai/blog/devsecops-ai-security-trojai-jfrog-integration
WitnessAIGuardrails / LLM FirewallPartialObserve discovers and catalogs AI apps, agents and MCP servers (usage inventory), not model supply-chain scanning.https://witness.ai/
CalypsoAIAI Red TeamingPartialF5/CalypsoAI blog: mitigates risks from outdated models, vulnerable pre-trained models, and weak model provenance via red-teaming and continuous monitoring — not full supply-chain artifact scanning.https://www.f5.com/company/blog/protecting-the-future-how-calypsoai-aligns-with-the-owasp-top-10-for-llms
KnosticAgentic AI SecurityPartialAgentMesh scans skills, MCP servers and VS Code extensions for supply-chain threats, but no model-file or dataset provenance control is documented.https://www.knostic.ai/agentmesh
AIR SecurityAgentic AI SecurityPartialAIR Filter scans add-on dependencies and sandboxes skills, but no model-file or dataset provenance control is documented.https://www.air.security/blog-posts/anthropic-scanner

2 vendors score Not covered and 1 score Unverified for LLM04 — see the full coverage matrix.

Open-source tools related to Supply Chain

These open-source projects also address supply chain, though we track them by repository health rather than scoring them like vendors:

Frequently asked questions

Which vendors cover LLM04 Supply Chain?

7 of the 27 vendors llmthreat tracks score Covered for LLM04 Supply Chain: Noma Security, Pillar Security, HiddenLayer, Protect AI, Apiiro, and others. 17 more score Partial, as of 2026-10-30.

What is LLM04 Supply Chain?

Compromised models, datasets, plugins, or dependencies add risk before runtime.

Last verified . Sources: OWASP LLM Top 10 (2026, CC BY-SA 4.0), vendor documentation. Funding and repo figures are third-party and go stale. Re-verify before you rely on them.
Informational, not professional security advice — coverage is llmthreat's editorial read of public documentation; verify each vendor's Supply Chain handling with the vendor directly before a decision. OWASP, MITRE, and the listed vendors and maintainers do not endorse llmthreat.com.