OWASP (Open Worldwide Application Security Project)
A nonprofit organization that publishes widely referenced application security standards, including the Top 10 for LLM Applications, which ranks the most critical risk categories for AI systems including prompt injection (LLM01).
Defined in 2 GAGE programs, which carry 3 distinct definitions of it. The wording above is taught in AI Data Governance: The Data Chair.
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 nonprofit organization that publishes widely referenced application security standards, including the Top 10 for LLM Applications, which ranks the most critical risk categories for AI systems including prompt injection (LLM01).
The organization whose Agentic Security Initiative authored the fifteen-threat taxonomy this and Topic 5.4 teach. The CSA Addendum adopts and reproduces this taxonomy; it is never CSA's own original research.
The nonprofit organization, best known for the OWASP Top 10 web-application risks, whose Agentic Security Initiative working group developed the fifteen-threat taxonomy CSA reproduces in Annex A.
Where it is taught
The exact lessons this term appears in. The first 7 topics of every program are free with a free account.
- The OWASP Threat Map I: Eight Ways an Agent Turns Against You · Technical Controls and Threat Modeling, Agentic AI Governance: Applied Mastery
- The OWASP Threat Map II · Technical Controls and Threat Modeling, Agentic AI Governance: Applied Mastery
- The injectable corpus: documents that attack the AI that reads them · Poison, Leaks, and the Adversary, AI Data Governance: The Data Chair
Terms it appears with
Not an alphabetical neighbourhood: these are the terms taught in the same lessons, ranked by how often they appear together.