LLM prompt injection test suite · 120 patterns
120 prompt injection patterns across 5 categories · with gold expected behaviour. Runs in CI. CC-BY.
Open prompt-injection eval dataset · 120 injection patterns in 5 categories (direct, indirect, RAG-poisoning, tool-abuse, exfiltration), each with expected behaviour + minimum pass rate. CC-BY.
WHAT'S INSIDE
- ·120 injection patterns in 5 categories
- ·Gold expected behaviour for each
- ·Compatible with Giskard / promptfoo
- ·CI integration example (GitHub Actions YAML)
- ·Hungarian + English language samples
Want a custom version?
A tailored audit or template delivered in 2 weeks · DField Solutions, Budapest.