CoreLayer AI Security logoCoreLayer AI Security

OWASP LLM Top 10

Every finding carries an OWASP LLM Top 10 identifier, so results line up with the framework your organisation already reports against.

The categories

IDCategoryCovered by
LLM01Prompt InjectionR-01, R-02, R-03; most TEST attack categories
LLM02Sensitive Information DisclosureR-06
LLM03Supply ChainVALIDATE: retrieval integrity
LLM04Data PoisoningR-08; VALIDATE: context isolation
LLM05Improper Output HandlingR-07; VALIDATE: output validation; TEST: output escape
LLM06Excessive AgencyR-04, R-05; VALIDATE: access control; RUNTIME: capability enforcement
LLM07Prompt LeakageTEST: system-prompt extraction
LLM08Vector and Embedding WeaknessesVALIDATE: RAG analysis
LLM09MisinformationR-09; RUNTIME: behavioural fingerprinting
LLM10Unbounded ConsumptionVALIDATE: context length bounds

Coverage by phase

No single phase covers the whole list, which is the point of having four. BUILD reaches what is visible in source; TEST reaches what is demonstrable against a live system; VALIDATE reaches deployment architecture; RUNTIME reaches what only shows up in production behaviour.

PhasePrimary categories
BUILDLLM01, LLM02, LLM04, LLM05, LLM06, LLM09
TESTLLM01, LLM05, LLM07
VALIDATELLM03, LLM05, LLM06, LLM08, LLM10
RUNTIMELLM06, LLM09

Running one phase is not full coverage

A clean BUILD scan means your source contains no detectable weakness. It says nothing about whether an attack succeeds against the deployed system, which is what TEST measures. Reports state which phases ran precisely so a clean result is not read as broader than it is.

Using the mapping

Filter dashboard findings by OWASP category when you need a framework view, such as “where are we on prompt injection?”. Reports carry the same breakdown, and the Compliance section maps posture against the list.

If your organisation reports under NIST AI RMF, ISO 42001, or an internal control set, use the OWASP identifier as a bridge. Most AI control mappings are already expressed against it.

Further reading

The authoritative list is maintained by OWASP at genai.owasp.org. SecureAI tracks it; the ruleset version and hash printed on every report record exactly which revision produced a given result.

Related: Scan rules · Scores & exit codes