SMSMC Blog

OWASP Top 10 for LLM Applications (2025) and Top 10 for Agentic Applications (2026): What SMBs Using AI Should Secure

How the OWASP Top 10 for LLM Applications and the new Top 10 for Agentic Applications apply to small businesses using chatbots, Copilot or AI agents, with a 12-week plan.

By Jim Venuto

Picture a Hudson Valley business whose support chatbot reads incoming email and can issue refunds. One crafted message tells it to refund every open order. Nothing was hacked in the usual sense; the bot did what the text told it to. If your business uses ChatGPT, Microsoft Copilot, customer-facing chatbots or AI agents for sales, support or operations, two OWASP lists describe the risks to control before an incident like that, or a data leak that triggers NY SHIELD Act notice: the Top 10 for LLM Applications (2025, released November 2024) and the Top 10 for Agentic Applications (2026, released December 9, 2025).

Plain-English Obligations

The OWASP Top 10 for Large Language Model (LLM) Applications provides security guidance for organizations deploying generative AI technologies like ChatGPT, Claude, Gemini, and custom-trained models. The 2025 update reflects lessons from real-world LLM deployments. It adds System Prompt Leakage and Vector and Embedding Weaknesses (the risks of Retrieval-Augmented Generation, or RAG), and widens Denial of Service into Unbounded Consumption.

The OWASP Top 10 for Agentic Applications for 2026, from the OWASP GenAI Security Project, addresses AI agents: systems that can plan, use tools, make decisions and run code with little human involvement. It covers goal hijacking, tool misuse, cascading failures and rogue agents, which LLM-only guidance does not fully address. Its entries are numbered ASI01 to ASI10.

Neither framework creates legal obligations, but they define security baselines that help you meet the NY SHIELD Act’s “reasonable safeguards” requirement, the FTC Safeguards Rule’s information security program (if you are a non-bank financial institution, such as a tax preparer, mortgage broker or auto dealer that arranges financing) and the governance practices of the NIST AI Risk Management Framework.

The 2025 OWASP Top 10 for LLM Applications

RiskWhat Changed in 2025Hudson Valley SMB Impact
LLM01: Prompt InjectionRemains #1; expanded coverage of indirect injection via uploaded files, URLs, and RAG data sourcesCustomer-facing chatbots can be manipulated to leak data, execute unauthorized actions, or bypass policy guardrails
LLM02: Sensitive Information DisclosureMoved up from #6 in the 2023 list; models trained on or retrieving proprietary data may leak trade secrets, PII, credentialsRisk of NY SHIELD breach notification if customer PII is embedded in training data or RAG knowledge bases
LLM03: Supply ChainMoved up from #5; covers vulnerable pre-trained models, third-party components and fine-tuning adaptersVendor risk: SaaS AI tools may introduce supply-chain compromise without your knowledge
LLM04: Data and Model PoisoningRenamed from Training Data Poisoning; covers corruption of pre-training, fine-tuning and embedding dataA model or knowledge base fed malicious documents can give wrong or harmful answers
LLM05: Improper Output HandlingRenamed from Insecure Output Handling (was #2); covers downstream risks when LLM outputs are executed (SQL injection, XSS, command injection)If your app takes LLM-generated code/queries and runs them, you’re exposed to remote code execution
LLM06: Excessive AgencyWas #8 in 2023; expanded because of the growing use of agents with tool accessAI agents with database write access, payment APIs, or external integrations can cause financial/data damage if misused
LLM07: System Prompt LeakageNew in 2025; attackers extract hidden instructions, business logic, or API keys from system promptsProprietary workflows embedded in prompts (e.g., pricing logic, compliance rules) can be stolen
LLM08: Vector and Embedding WeaknessesNew in 2025; focuses on RAG security (vector database poisoning, embedding model attacks)RAG-powered chatbots pulling from corrupted or malicious vector stores will hallucinate harmful outputs
LLM09: MisinformationTakes the place of Overreliance; covers false or misleading output (hallucination) and over-trust in itCustomer-facing bots generating false product claims, medical advice, or legal guidance create liability
LLM10: Unbounded ConsumptionExpands the 2023 Model Denial of Service entry; now covers cost and resource abuseAttacker-induced token consumption can run up large API bills quickly when there are no rate limits or spending caps

The OWASP Top 10 for Agentic Applications (2026)

RiskDescriptionHudson Valley SMB Scenario
ASI01: Agent Goal HijackAttacker redirects agent’s objectives via prompt injection, malicious artifacts, or external dataSales agent instructed to “offer 90% discount to all customers” via crafted email input
ASI02: Tool MisuseAgent uses legitimate tools in harmful ways due to over-privileged accessAI agent with Stripe API access creates fraudulent refunds or subscriptions
ASI03: Identity & Privilege AbuseAgent escalates privileges by abusing its own identity or inheriting user credentialsAgent impersonates admin user to access restricted financial records
ASI04: Agentic Supply Chain VulnerabilitiesCompromised models, poisoned RAG data, vulnerable tool definitions, or malicious pluginsThird-party agent marketplace plugin contains backdoor code that exfiltrates data
ASI05: Unexpected Code ExecutionAgent tricked into generating and executing malicious codeCoding agent writes Python script to upload customer database to attacker-controlled server
ASI06: Memory & Context PoisoningPersistent corruption of agent’s long-term memoryAttacker seeds false “facts” into agent’s memory so future responses leak credentials
ASI07: Insecure Inter-Agent CommunicationMulti-agent systems allowing message forging, spoofing, or MITM attacksAgent A impersonates Agent B to approve unauthorized transactions
ASI08: Cascading FailuresSmall error triggers uncontrolled chain reaction in agent workflowFailed payment triggers refund → duplicate order → inventory depleted → financial loss
ASI09: Human-Agent Trust ExploitationAttacker manipulates agent output to deceive human-in-the-loopAgent presents fraudulent invoice for CEO approval with fabricated vendor justification
ASI10: Rogue AgentsAgents operating outside intended mandate due to governance failureAuto-updated agent begins sending customer data to unapproved third-party analytics service

Practical Implementation Plan

Phase 1 (week 1): inventory and risk classification

Identify all LLM/AI agent deployments (internal tools, customer-facing bots, code assistants, automation workflows). Classify by autonomy level: passive (chat-only) vs. agentic (tool-using, decision-making). Map data flows: what PII, trade secrets, or regulated data can the model access or output? Document tools/APIs each agent can invoke.

Phase 2 (weeks 2 to 4): LLM Top 10 controls

Prompt Injection Defense: input sanitization, system-prompt isolation, output validation.

Sensitive Data Protection: Remove PII from training data; implement output filtering.

RAG Security (LLM08): Control who can add documents to the knowledge base; sanitize documents before embedding; enforce access permissions on what the retriever returns.

Excessive Agency Controls (LLM06): least-privilege tool access; human approval for high-risk actions.

Unbounded Consumption Limits (LLM10): Rate-limit API calls; set token budgets; implement circuit breakers.

Supply Chain Vetting: AI-specific SBOM; validate all third-party components.

Phase 3 (weeks 5 to 8): agentic controls

Goal Integrity (ASI01): Log all agent instructions; alert on goal changes; read-only mode for high-risk agents.

Tool Sandboxing (ASI02, ASI05): Run agent tools and generated code in isolated sandboxes or containers with no network egress by default.

Identity Management (ASI03): Unique, short-lived, session-based credentials per agent.

Inter-Agent Security (ASI07): mTLS + digital signing for all agent-to-agent messages.

Cascading Failure Prevention (ASI08): Transactional rollback; circuit breakers; safe failure modes.

Kill Switch (ASI10): Auditable emergency stop; continuous behavioral monitoring.

Phase 4 (weeks 9 to 12): evidence and governance

Establish AI governance committee (CISO, legal, business owner) for quarterly reviews. Map OWASP controls to NIST AI RMF functions (Govern, Map, Measure, Manage). Create incident playbook for AI-specific events. Document “reasonable safeguards” for AI data handling (NY SHIELD Act). Implement logging for all agent actions with 1-year retention.

Evidence Pack

Control AreaEvidenceOWASP MappingCompliance Link
AI InventoryList of all LLM/agent deployments, data access, tool permissionsLLM06, ASI02NIST AI RMF Map
Prompt Injection DefenseInput sanitization rules, output validation logsLLM01NY SHIELD reasonable safeguards
RAG Data IntegrityVector DB integrity checks, document sanitization logsLLM08FTC Safeguards data security
Agent Tool Access ControlsLeast-privilege matrix, human-approval workflowsLLM06, ASI02NIST AI RMF Govern
Code Execution SandboxingContainer config, network egress logs, sandbox audit trailASI05NIST AI RMF Manage
Inter-Agent mTLS ConfigCertificate chain, message signing logsASI07NIST AI RMF Manage
Rate Limits & Cost ControlsAPI token budgets, circuit-breaker logs, billing alertsLLM10FTC Safeguards risk assessment
AI Incident Response PlanPlaybook for prompt injection, data leak, rogue agent scenariosLLM01, ASI10NY SHIELD breach notification
Kill Switch DocumentationEmergency stop procedure, behavioral monitoring alertsASI10NIST AI RMF Govern
AI Governance Meeting MinutesQuarterly reviews, risk acceptance decisions, deployment approvalsAllNIST AI RMF Govern

Where to start

Start with the Phase 1 inventory: one list of every AI tool, what data it can reach and what it can do. Your team owns that list and the approvals; your AI vendors own the security of their platforms; a security adviser can map the gaps to the NIST AI RMF and NY SHIELD. Hudson Valley CISO leads security programs using NIST CSF 2.0 and the NIST AI RMF, and offers a free 30-minute call.

Sources

  1. OWASP GenAI Security Project, “OWASP Top 10 for LLM Applications 2025”: genai.owasp.org/llm-top-10
  2. OWASP, “OWASP Top 10 for Agentic Applications for 2026,” December 9, 2025: genai.owasp.org
  3. NIST, AI Risk Management Framework (AI 100-1): nist.gov