kate8382

kate8382/AURA

AURA: Behavioral matrices and validation tooling to detect manipulation, social engineering, and grey-zone threats in LLM interactions.

1 stars 0 forks 1 watchers TypeScript Other
behavioral-dataset case-generator deception llm-interactions prompt-manipulation threat-matrices validation-library
View on GitHub
2 Open Issues Need Help Last updated: Sep 17, 2026

Open Issues Need Help

View All on GitHub
Add example CLI/SDK and `examples/` end-to-end demo 2 days ago
documentation enhancement good first issue
kate8382/AURA
1

AURA: Behavioral matrices and validation tooling to detect manipulation, social engineering, and grey-zone threats in LLM interactions.

TypeScript
#behavioral-dataset#case-generator#deception#llm-interactions#prompt-manipulation#threat-matrices#validation-library
Trigger extraction from `scenarios[].text` (lightweight NLP heuristics) 5 days ago
enhancement good first issue feature
kate8382/AURA
1

AURA: Behavioral matrices and validation tooling to detect manipulation, social engineering, and grey-zone threats in LLM interactions.

TypeScript
#behavioral-dataset#case-generator#deception#llm-interactions#prompt-manipulation#threat-matrices#validation-library