Australian Information Security Manual
Guidelines for software development

Australian Information Security Manual ISM-1924: Generative artificial intelligence applications evaluate user prompts to detect and mitiga

Generative artificial intelligence applications evaluate user prompts to detect and mitigate adversarial inputs or suffixes designed to elicit unintended behaviour or assist in the generation of sensitive or harmful content.

Maintained by Gerard BlokdykVerified against the published standard Control text last updated

Other controls in Guidelines for software development

Query this from an agent

The graph holds this control, the 0 it maps to, and the evidence behind each claim, over MCP and REST.