Open Issues Need Help
View All on GitHub good first issue catalog
Mihirajmera/llm-redteam-evidence Mihirajmera/llm-redteam-evidence Turn LLM red-team results (garak, promptfoo) into audit evidence: per-control pass/fail with risk tolerance and confidence bounds, hashed evidence, OSCAL, and a model release gate. OWASP LLM Top 10 · MITRE ATLAS · NIST AI 600-1
Open project →
0
Turn LLM red-team results (garak, promptfoo) into audit evidence: per-control pass/fail with risk tolerance and confidence bounds, hashed evidence, OSCAL, and a model release gate. OWASP LLM Top 10 · MITRE ATLAS · NIST AI 600-1
Python
#ai-governance#ai-red-teaming#ai-security#compliance-as-code#garak#grc-engineering#llm-security#mitre-atlas#nist-ai-600-1#nist-ai-rmf#oscal#owasp-llm-top-10#promptfoo#python#red-teaming
Support PyRIT results as an input format 8 days ago
help wanted
Mihirajmera/llm-redteam-evidence Mihirajmera/llm-redteam-evidence Turn LLM red-team results (garak, promptfoo) into audit evidence: per-control pass/fail with risk tolerance and confidence bounds, hashed evidence, OSCAL, and a model release gate. OWASP LLM Top 10 · MITRE ATLAS · NIST AI 600-1
Open project →
0
Turn LLM red-team results (garak, promptfoo) into audit evidence: per-control pass/fail with risk tolerance and confidence bounds, hashed evidence, OSCAL, and a model release gate. OWASP LLM Top 10 · MITRE ATLAS · NIST AI 600-1
Python
#ai-governance#ai-red-teaming#ai-security#compliance-as-code#garak#grc-engineering#llm-security#mitre-atlas#nist-ai-600-1#nist-ai-rmf#oscal#owasp-llm-top-10#promptfoo#python#red-teaming
good first issue
Mihirajmera/llm-redteam-evidence Mihirajmera/llm-redteam-evidence Turn LLM red-team results (garak, promptfoo) into audit evidence: per-control pass/fail with risk tolerance and confidence bounds, hashed evidence, OSCAL, and a model release gate. OWASP LLM Top 10 · MITRE ATLAS · NIST AI 600-1
Open project →
0
Turn LLM red-team results (garak, promptfoo) into audit evidence: per-control pass/fail with risk tolerance and confidence bounds, hashed evidence, OSCAL, and a model release gate. OWASP LLM Top 10 · MITRE ATLAS · NIST AI 600-1
Python
#ai-governance#ai-red-teaming#ai-security#compliance-as-code#garak#grc-engineering#llm-security#mitre-atlas#nist-ai-600-1#nist-ai-rmf#oscal#owasp-llm-top-10#promptfoo#python#red-teaming