Every finding carries the LLM-NN identifier and the OWASP CWE references that underpin it
.
OWASP LLM Top 10 (2025) is the community-curated list of the most critical security risks for large-language-model applications, covering LLM01 (prompt injection) through LLM10 (model theft).
Last reviewed July 2026
An auditor works from a framework control list; a scan produces a finding list. Without a mapping between the two, each finding has to be translated onto the controls by hand before an audit.
Penaxtra ships probe families across all ten categories. The runtime gateway enforces controls aligned to LLM02, LLM06, LLM07, and LLM08.
.
A successful indirect-injection probe via a RAG document is tagged LLM01 (prompt injection) and cross-mapped to LLM06 (sensitive disclosure) when the response leaked context.
Each control has a dedicated page: what it covers and how Penaxtra tests and evidences it.