Docs

Appearance

OWASP Top 10 for Agentic Applications (2026) ​

OWASP Top 10 for Agentic Applications illustration

The OWASP Top 10 for Agentic Applications is a practical security taxonomy for agentic AI applications: systems that plan, act, and use tools across multi-step workflows (including multi-agent orchestration).

Related framework

Most agentic systems are also LLM apps. For the LLM-focused taxonomy, see OWASP Top 10 for LLM Applications (2025).

Key facts
Type
Security risk taxonomy
Scope
Agentic AI applications
Focus
Autonomy, tool use, delegation
Version
2026 (ASI)
Best for
Security and engineering teams

Authoritative resources ​

Why agentic security matters in governance ​

Agentic systems expand the attack surface because outputs can turn into actions:

  • tool calls and side effects (data access, execution, external actions)
  • delegation chains and inherited privileges
  • memory that persists across sessions
  • inter-agent messaging and discovery
  • cascading failures with fast fan-out

Go deeper:

Agentic app attack surface (quick map) ​

Agentic app attack surface (where risks show up)
Inputs and goal settingprompts, retrieved content, tool outputs, messages
ASI01 Agent Goal Hijack
ASI09 Human-Agent Trust Exploitation
Planning and orchestrationmulti-step plans, task graphs, sub-agents
ASI08 Cascading Failures
ASI10 Rogue Agents
Tools and actionsfunction calling, plugins, automation, permissions
ASI02 Tool Misuse and Exploitation
ASI05 Unexpected Code Execution
Identity and delegationagent identities, scopes, delegation chains
ASI03 Identity and Privilege Abuse
ASI09 Human-Agent Trust Exploitation
Supply chain and registriestools, prompts, agent cards, MCP servers, artifacts
ASI04 Agentic Supply Chain Vulnerabilities
Memory and contextRAG, embeddings, long-term memory, summaries
ASI06 Memory & Context Poisoning
Inter-agent communicationcoordination protocols, discovery, messaging
ASI07 Insecure Inter-Agent Communication

How Modulos operationalizes OWASP work ​

In Modulos, OWASP becomes executable governance:

  • represent OWASP categories as requirements and mapped controls
  • link evidence (design docs, red-team results, incident records)
  • run tests and store results as governance signals

Related platform areas:

Getting started ​

Top risks

A practical overview of ASI01–ASI10

Mitigations and testing

Turn OWASP into controls, evidence, and tests in Modulos

Testing

Turn evaluations into governance signals

Disclaimer

This page is for general informational purposes and does not constitute legal advice or security advice.