NuGuardAI

NuGuardAI/nuguard

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

15 stars 6 forks 15 watchers Python Other

adversarial-machine-learning agentic-ai ai-agents ai-red-team-tool ai-red-teaming ai-security ai-tools genrative-ai jailbreak llm llm-evaluation llm-secuirty mcp mcp-server owasp prompt-injections sbom sbom-generator static-analysis vulnerability-assessment

View on GitHub Website

24 Open Issues Need Help Last updated: Jul 31, 2026

Open Issues Need Help

View All on GitHub

Generalized approach to redteaming about 1 hour ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

Remove nuguard/redteam/v2 — unmaintained, unverified engine reachable via --engine v2 about 18 hours ago

enhancement good first issue help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

[C# Support] Semgrep rules for C# AI security anti-patterns about 18 hours ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

[C# Support] Test fixtures and unit tests for C# adapters about 18 hours ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

[C# Support] Wire C# parsing into the SBOM extraction pipeline about 18 hours ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

[C# Support] C# parse result infrastructure and framework adapter base class about 18 hours ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

[C# Support] C# framework adapters (LLM clients, Semantic Kernel, ASP.NET Core) about 18 hours ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

Add C# Support to NuGuard Pipeline about 18 hours ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

[Go Support] Go AI framework adapters (langchaingo, mcp-go, eino) 1 day ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

[Go Support] Go parse result infrastructure (go_parser.py) 2 days ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

[Go Support] GoFrameworkAdapter base class 3 days ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

[Go Support] Semgrep rules for Go AI security anti-patterns 3 days ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

nuguard policy show always reports 'not found' 4 days ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

[Go Support] Add .go to file extension whitelist and go.mod dependency scanning 5 days ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

Add Golang Support to NuGuard Pipeline 5 days ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

[Go Support] Wire Go parsing into the SBOM extraction pipeline 6 days ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

[Go Support] Test fixtures and unit tests for Go adapters 6 days ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

[Go Support] Go LLM client adapters (go-openai, anthropic-sdk-go, google/generative-ai-go) 6 days ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

[Go Support] Go web framework adapters for API endpoint detection (Gin, Echo, net/http) 6 days ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

endpoint-resolution-precedence-plan.md still says Status: Planned, but the fix already shipped 7 days ago

documentation good first issue

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

Misleading skip-reason comment in redteam scenario selector 7 days ago

good first issue

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

nuguard seed/report/findings/replay are stub commands with no backing model 7 days ago

enhancement help wanted

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

Stale RedteamV2Settings docstring contradicts orchestrator.py 7 days ago

documentation good first issue

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment

CLAUDE.md claims Postgres support that doesn't exist 7 days ago

documentation good first issue

NuGuardAI/nuguard

15

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Python

#adversarial-machine-learning#agentic-ai#ai-agents#ai-red-team-tool#ai-red-teaming#ai-security#ai-tools#genrative-ai#jailbreak#llm#llm-evaluation#llm-secuirty#mcp#mcp-server#owasp#prompt-injections#sbom#sbom-generator#static-analysis#vulnerability-assessment