guardrail-arena fevziegeyurtsevenler · COMPLETED
Two-axis, multilingual (EN+TR) benchmark for LLM prompt-injection guardrails: measures attack miss-rate AND over-refusal on security-adjacent text. Any guardrail is a callable.
github.com/fevziegeyurtsevenler/guardrail-arena · ★ 0 · Forks 0 · Size 145 KB
SUMMARY
Technologies 6
Scored 6
Observed 6
Practices 6
Evidence 7
Skips 0
COVERAGE
Analyzed 28 files · 9 commits · 0 API calls
TECHNOLOGIES & DEPTH
JSON LANGUAGE Depth 70
2 files · PRODUCTION
Markdown LANGUAGE Depth 70
2 files · PRODUCTION
XML LANGUAGE Depth 70
1 files · PRODUCTION
YAML LANGUAGE Depth 70
7 files · PRODUCTION
Python LANGUAGE Depth 70
6 files · PRODUCTION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · absentlinting · absentformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-07-26
Last commit 2026-08-08
Active months 2
Commits 9