OWASP Top 10 for LLM Applications
A published, community-maintained list of the top security risks for applications built on large language models (2025 edition), used here as the shared reference for the attack families. Prompt injection (LLM01) sits at the top for the second edition running.
Defined in 2 GAGE programs, which carry 3 distinct definitions of it. The wording above is taught in Certified AI Governance Professional (CAIGP).
How each discipline defines it
The same term does different work depending on who is using it. These are the definitions as each program teaches them, unedited.
A published, community-maintained list of the top security risks for applications built on large language models (2025 edition), used here as the shared reference for the attack families. Prompt injection (LLM01) sits at the top for the second edition running.
The recognized industry catalog of the most critical security vulnerability classes in systems that use large language models, updated for 2025 by the OWASP Gen AI Security Project; the awareness-level reference behind the Security Awareness Check.
A widely used industry catalog of the top security risks for AI applications, in which prompt injection (LLM01) is ranked number one (OWASP Gen AI Security Project, 2025) (see Topic 8.5).
Where it is taught
The exact lessons this term appears in. The first module of every program is free with a free account.
- ROI and Security Mastery Checks · Assessment and Continuous Learning, Certified AI Practitioner: Workplace Foundations
- Prompt Injection and Jailbreak Defense · AI Security Fundamentals, Certified AI Practitioner: Workplace Foundations
- Red-teaming your own system: attacks a motivated user will find · Evaluation and Trust, Certified AI Governance Professional (CAIGP)
Where it shows up at work
A definition is where OWASP Top 10 for LLM Applications starts. The lessons above teach it inside the competencies below, which are what job descriptions ask for and what the GAGE credential records. Every link here is drawn from the same careers map that builds a role's readiness check.
Understands prompt injection, data poisoning, model theft, insecure integrations and excessive agent privileges, and the controls that reduce each.
One lesson on this page teach it as a primary outcome.
Builds an honest value model: baseline, measured change, cost, risk, and the projects that should be stopped.
One lesson on this page teach it as a primary outcome.
Finds unapproved AI use, sets which tools are approved and what may be pasted, and detects leakage without policing every keystroke.
One lesson on this page teach it as a primary outcome.
Roles that hire for it
Each role page shows the full competency set, what the seat decides, and a readiness check against your own evidence.
- Cybersecurity Risk Analystneeds working knowledge
- Chief Information Security Officer, AI security focusneeds it at depth
- Chief Technology Officer, AI engineering editionneeds it at depth
- AI Incident Response Leadneeds it at depth · 1 open posting this week
- AI Security Architectneeds it at depth · 8 open postings this week
- AI Governance Engineerneeds it at depth · 7 open postings this week
How job descriptions say it
Postings rarely use the textbook word. These are the phrases the careers map reads as asking for the competencies above.
Where the frameworks place it: OWASP Top 10 for LLM Applications; Google SAIF; NIST AI RMF MEASURE 2; ISO/IEC 27001 Annex A.
One interview question about it
What are the security failure modes specific to AI systems, and which conventional control covers none of them?
Asked of candidates for ai security fundamentals. Answering it in your own words is exactly how a GAGE topic is passed, and the credential records the pass where an employer can check it.
If you come from another field
Some backgrounds already carry this competency, and the readiness check gives credit for it.
- Cybersecurity and IT carries it as a claim to back up: Threat modeling and control design transfer; the AI-specific threats are new.
- A computer science or software engineering degree carries it as a claim to back up: Security fundamentals are a course you took, not yet a control you ran.
- A cybersecurity or information assurance degree carries it as work you can show: Security fundamentals are your coursework and your labs.
Terms it appears with
Not an alphabetical neighbourhood: these are the terms taught in the same lessons, ranked by how often they appear together.