{"slug":"mukul975-continuous-llm-red-teaming-with-promptfoo","source_name":"mukul975/continuous-llm-red-teaming-with-promptfoo","name":"Mukul975/Continuous LLM Red Teaming With Promptfoo","description":"Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.","version":1,"lift":{"pass_rate_delta_pts":22.73,"pass_rate_pct":90.9,"total_cases":22,"passed_cases":20,"tokens_delta_pct":137.1,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-03T19:25:49.856731+00:00"},"skill_score":0.9091,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":22.73,"with_pass_pct":90.9,"without_pass_pct":68.2,"tokens_delta_pct":137.1,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-03T19:25:49.856731+00:00","run_id":"061601f5-d427-46e5-b454-79f2b2ab5a91","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"Apache-2.0","install_count":0,"manifest_hash":"bd2a41e69ac18931f05ec610b3522fd1d1d6b9891e22182c811639dfc159036f","raw_url":"https://app.decimal.ai/s/mukul975-continuous-llm-red-teaming-with-promptfoo/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/mukul975-continuous-llm-red-teaming-with-promptfoo"}