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 June 2026
Auditors arrive with the framework control list. Security teams arrive with a finding list. Without a pre-computed mapping, every finding requires manual translation.
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.
Scoped walkthrough of the Compliance / OWASP LLM Top 10 surface against your environment. No credit card.