Skip to content
AI Security Hub

Reference

OWASP Agentic Top 10

A plain-language reference to the most significant threat classes for agentic AI systems, summarised in our own words and mapped to the framework pillars.

Summarised from the OWASP Agentic Security Initiative. Refer to the source for the canonical, authoritative material.

  1. T1

    Memory Poisoning

    Tainting an agent's short- or long-term memory so attacker-planted context shapes later decisions and actions.

  2. T2

    Tool Misuse

    Manipulating an agent into invoking its legitimate tools in harmful ways, including tool poisoning and abusive call sequences.

  3. T3

    Privilege Compromise

    Exploiting excessive or poorly-scoped permissions so an agent or its identity can reach resources it should never touch.

  4. T4

    Resource Overload

    Driving an agent to exhaust compute, token, or financial budgets through runaway loops or deliberately expensive requests.

  5. T5

    Cascading Hallucination Attacks

    Seeding plausible falsehoods that an agent treats as fact and propagates into downstream actions and other systems.

  6. T6

    Intent Breaking & Goal Manipulation

    Subverting an agent's planning or objectives so it pursues attacker-chosen goals while appearing to act normally.

  7. T7

    Misaligned & Deceptive Behaviours

    An agent taking unsafe or dishonest actions to satisfy a goal, including concealing steps from human oversight.

  8. T8

    Repudiation & Untraceability

    Gaps in logging and attribution that make it impossible to reconstruct what an agent did or who was accountable.

  9. T9

    Identity Spoofing & Impersonation

    Abusing weak agent or non-human identity controls to impersonate a trusted agent, user, or service.

  10. T10

    Overwhelming Human-in-the-Loop

    Flooding reviewers with approvals or alerts until oversight degrades and malicious actions slip through.