GenAIHub
← Back to Technical Section

OWASP for LLM & Agentic AI

The Industry Benchmark for Securing LLM Applications and Autonomous Agents

What is OWASP for GenAI?

The OWASP GenAI Security Project maintains the de-facto standard for AI security risk: the OWASP Top 10 for LLM Applications (2025 edition) and, building on it, the OWASP Top 10 for Agentic Applications (released December 2025). Together they give builders a shared vocabulary to identify, prioritize and mitigate the threats unique to LLM-powered and autonomous-agent systems — from prompt injection to rogue agents.

"Agency is power. The more autonomy, tools and memory you give an agent, the larger its attack surface. OWASP frames these risks so you can defend them deliberately, not discover them in production."

— OWASP GenAI Security Project

Injection

Direct & indirect

Tool Abuse

Weaponized actions

Excess Privilege

Least-privilege

Data Leakage

Sensitive info

Key OWASP Risks for Agentic AI

OWASP identifies several risk categories specific to LLM- and agent-based systems. These are the ones that matter most when an agent can plan, call tools and act autonomously:

1 Prompt Injection

A user or external content manipulates the agent's behavior. Example: an email received by the agent contains hidden instructions to ignore its safety rules (indirect injection).

2 Tool Abuse

Misuse of the tools available to the agent. Example: an agent with Gmail access sends emails without proper authorization.

3 Excessive Permissions

The agent holds more privileges than it should — a violation of the principle of least privilege.

4 Data Leakage

Exposure of sensitive information. Internal data can be sent to external APIs or shown to the user.

5 RAG Poisoning

Manipulation of the knowledge base the agent relies on. Malicious documents influence answers and decisions.

6 Supply Chain Attacks

Compromised libraries, models or tools — especially relevant in LangChain, MCP and plugin ecosystems.

7 Agent Hijacking

The agent's decision flow is altered to execute unauthorized tasks (OWASP "Agent Goal Hijack").

OWASP Top 10 for LLM Applications (2025)

Code Risk What It Covers
LLM01Prompt InjectionDirect & indirect inputs overriding intended behavior
LLM02Sensitive Information DisclosureLeaking PII, secrets, proprietary data via outputs
LLM03Supply ChainCompromised models, datasets, libraries, plugins
LLM04Data & Model PoisoningTampered training/fine-tuning data corrupting behavior
LLM05Improper Output HandlingUnvalidated output causing XSS, SSRF, RCE downstream
LLM06Excessive AgencyToo much autonomy, permissions or tool access
LLM07System Prompt LeakageExposure of hidden system instructions/secrets
LLM08Vector & Embedding WeaknessesRAG/vector-DB attacks (incl. RAG poisoning)
LLM09MisinformationConfidently wrong / hallucinated outputs
LLM10Unbounded ConsumptionResource exhaustion, denial-of-wallet, DoS

OWASP Top 10 for Agentic Applications (2025)

The agentic list (codes ASI01–ASI10) covers new attack surfaces introduced by autonomy, tools, memory and multi-agent coordination.

Code Threat Real-World Example
ASI01Agent Goal HijackHidden prompts redirect the agent (EchoLeak)
ASI02Tool MisuseLegitimate tools weaponized (Amazon Q)
ASI03Identity & Privilege AbuseLeaked credentials expand operational scope
ASI04Agentic Supply ChainCompromised runtime components (GitHub MCP exploit)
ASI05Unexpected Code ExecutionNatural language → RCE (AutoGPT RCE)
ASI06Memory & Context PoisoningPersisted data alters future behavior (Gemini memory attack)
ASI07Insecure Inter-Agent CommunicationSpoofed messages misdirect coordination
ASI08Cascading FailuresFalse signals compound through automated workflows
ASI09Human-Agent Trust ExploitationPolished explanations get harmful actions approved
ASI10Rogue AgentsMisaligned, self-directed behavior (Replit meltdown)

Defense Playbook

Do This

  • Apply least privilege to every tool & credential
  • Treat all external content (email, web, docs) as untrusted
  • Require human approval for high-impact actions (HITL)
  • Validate & sanitize LLM output before it hits other systems
  • Sign & pin models, plugins and MCP servers
  • Log, trace and red-team continuously (e.g. Promptfoo)

Avoid This

  • Giving agents broad, standing write access
  • Trusting retrieved documents without provenance checks
  • Installing unvetted plugins/MCP servers
  • Letting agents auto-approve their own destructive actions
  • Putting secrets in system prompts
  • Shipping without rate/cost limits

Resources

OWASP Top 10 for LLMs

Official 2025 list, PDFs and mitigation guidance.

genai.owasp.org/llm-top-10 →

Agentic AI Threats

Top 10 for Agentic Applications and the Threats & Mitigations taxonomy.

genai.owasp.org/agentic →

Related Topics