Make it safe.
Software against prompt injection, data leaks and deepfakes.
Start here
Hive AI-Generated Content DetectionMake it safe · HiveQuickly check whether an image or song is AI-madeFree versionTrust high, 100Beginner-friendlyLumo by ProtonMake it safe · Proton AGAn AI assistant that keeps your chats privateFree versionTrust high, 100Beginner-friendlyReality DefenderMake it safe · Reality Defender Inc.Detect deepfakes in voice, images and videoFree versionTrust high, 100Beginner-friendly
Coding
garakMake it safe · NVIDIAHave your language model attacked on purposeOpen SourceTrust high, 100For developersGuardrails AIMake it safe · Guardrails AI (Harvey)Check AI answers before they move onOpen SourceTrust high, 100For developersNeMo GuardrailsMake it safe · NVIDIAFirm guardrails for your chatbotOpen SourceTrust high, 100For developersGiskardMake it safe · GiskardScan LLM apps for hallucinations and leaksOpen SourceTrust high, 100For developersPyRITMake it safe · Microsoft (AI Red Team)Automate red teaming for generative AIOpen SourceTrust high, 100For developersMeta PurpleLlama (Llama Guard 4, Prompt Guard 2, LlamaFirewall)Make it safe · MetaFree guard models for your own AIOpen SourceTrust high, 100Runs offlinepromptfooMake it safe · Promptfoo (OpenAI)Test AI features like regular codeOpen SourceTrust high, 97For developersSnyk Agent Scan (formerly Invariant MCP-Scan)Make it safe · Snyk (ex-Invariant Labs team)Scan installed MCP servers and skills for trapsOpen SourceTrust high, 100For developersCisco Skill ScannerMake it safe · Cisco AI DefenseCheck agent skills before you install themOpen SourceTrust high, 100For developersDocker MCP GatewayMake it safe · DockerRun MCP servers sealed off in containersOpen SourceTrust high, 100For developersCisco MCP ScannerMake it safe · Cisco AI DefenseInspect MCP servers before you plug them inOpen SourceTrust high, 100For developersModelScanMake it safe · Protect AI (Palo Alto Networks)Check model files before you load themOpen SourceTrust high, 100Runs offline
AI agents
Cisco AI DefenseMake it safe · CiscoSee and secure AI use across your companyPaidTrust high, 100For businessesF5 AI Guardrails & AI Red Team (formerly CalypsoAI)Make it safe · F5 (CalypsoAI)Runtime protection and attack tests for company AIPaidTrust high, 100For businessesHiddenLayer AISec PlatformMake it safe · HiddenLayerProtect your own models and agents in productionPaidTrust high, 100For businessesLakera GuardMake it safe · Lakera (Check Point Software)Catch prompt attacks before your AI respondsFree versionTrust high, 100For businessesMindgardMake it safe · MindgardAttack your AI continuously instead of testing oncePaidTrust high, 100For businessesTrojAIMake it safe · TrojAI (A10 Networks)Test AI models and monitor agent trafficPaidTrust high, 100For businessesZenityMake it safe · ZenityDecide what your AI agents are allowed to doPaidTrust high, 100For businessesAktoMake it safe · AktoFind and test MCP servers and APIs in your companyOpen SourceTrust high, 97For developersLasso SecurityMake it safe · Lasso SecurityKeep an eye on your own AI apps and agentsPaidTrust high, 92For businessesNoma SecurityMake it safe · Noma SecurityVisibility and control over all your AI agentsPaidTrust high, 92For businessesPillar SecurityMake it safe · Pillar SecurityFind, test and protect every AI componentPaidTrust high, 92For businessesPrisma AIRSMake it safe · Palo Alto NetworksSecure AI models, apps and agents with one vendorPaidTrust high, 92For businesses
Security
Cloudflare AI Security for Apps (formerly Firewall for AI)Make it safe · CloudflareProtect AI endpoints right at the web firewallPaidTrust high, 100For businessesGoogle Cloud Model ArmorMake it safe · Google CloudOne filter for prompts and answers, whatever the modelFree versionTrust high, 100For developersHarmonic SecurityMake it safe · Harmonic SecurityKeep company data out of third-party AI toolsPaidTrust high, 100For businessesHive AI-Generated Content DetectionMake it safe · HiveQuickly check whether an image or song is AI-madeFree versionTrust high, 100Beginner-friendlyLumo by ProtonMake it safe · Proton AGAn AI assistant that keeps your chats privateFree versionTrust high, 100Beginner-friendlyMicrosoft Prompt Shields (Azure AI Content Safety)Make it safe · MicrosoftDetect prompt attacks hidden in documentsPaidTrust high, 100For developersPrompt SecurityMake it safe · Prompt Security (SentinelOne)See which AI your team uses and protect your dataPaidTrust high, 100For businessesReality DefenderMake it safe · Reality Defender Inc.Detect deepfakes in voice, images and videoFree versionTrust high, 100Beginner-friendlySensityMake it safe · SensityHave suspicious media examined forensicallyPaidTrust high, 100For businessesSocketMake it safe · SocketStop malicious packages before they reach your codeFree versionLimited checks · 2 checksFor developers
Packages with this software
All 34
34 products
garakMake it safe · NVIDIAHave your language model attacked on purposeOpen SourceTrust high, 100For developersGuardrails AIMake it safe · Guardrails AI (Harvey)Check AI answers before they move onOpen SourceTrust high, 100For developersNeMo GuardrailsMake it safe · NVIDIAFirm guardrails for your chatbotOpen SourceTrust high, 100For developersGiskardMake it safe · GiskardScan LLM apps for hallucinations and leaksOpen SourceTrust high, 100For developersPyRITMake it safe · Microsoft (AI Red Team)Automate red teaming for generative AIOpen SourceTrust high, 100For developersMeta PurpleLlama (Llama Guard 4, Prompt Guard 2, LlamaFirewall)Make it safe · MetaFree guard models for your own AIOpen SourceTrust high, 100Runs offlinepromptfooMake it safe · Promptfoo (OpenAI)Test AI features like regular codeOpen SourceTrust high, 97For developersSnyk Agent Scan (formerly Invariant MCP-Scan)Make it safe · Snyk (ex-Invariant Labs team)Scan installed MCP servers and skills for trapsOpen SourceTrust high, 100For developersCisco Skill ScannerMake it safe · Cisco AI DefenseCheck agent skills before you install themOpen SourceTrust high, 100For developersDocker MCP GatewayMake it safe · DockerRun MCP servers sealed off in containersOpen SourceTrust high, 100For developersCisco MCP ScannerMake it safe · Cisco AI DefenseInspect MCP servers before you plug them inOpen SourceTrust high, 100For developersModelScanMake it safe · Protect AI (Palo Alto Networks)Check model files before you load themOpen SourceTrust high, 100Runs offlineCisco AI DefenseMake it safe · CiscoSee and secure AI use across your companyPaidTrust high, 100For businessesCloudflare AI Security for Apps (formerly Firewall for AI)Make it safe · CloudflareProtect AI endpoints right at the web firewallPaidTrust high, 100For businessesF5 AI Guardrails & AI Red Team (formerly CalypsoAI)Make it safe · F5 (CalypsoAI)Runtime protection and attack tests for company AIPaidTrust high, 100For businessesGoogle Cloud Model ArmorMake it safe · Google CloudOne filter for prompts and answers, whatever the modelFree versionTrust high, 100For developersHarmonic SecurityMake it safe · Harmonic SecurityKeep company data out of third-party AI toolsPaidTrust high, 100For businessesHiddenLayer AISec PlatformMake it safe · HiddenLayerProtect your own models and agents in productionPaidTrust high, 100For businessesHive AI-Generated Content DetectionMake it safe · HiveQuickly check whether an image or song is AI-madeFree versionTrust high, 100Beginner-friendlyLakera GuardMake it safe · Lakera (Check Point Software)Catch prompt attacks before your AI respondsFree versionTrust high, 100For businessesLumo by ProtonMake it safe · Proton AGAn AI assistant that keeps your chats privateFree versionTrust high, 100Beginner-friendlyMicrosoft Prompt Shields (Azure AI Content Safety)Make it safe · MicrosoftDetect prompt attacks hidden in documentsPaidTrust high, 100For developersMindgardMake it safe · MindgardAttack your AI continuously instead of testing oncePaidTrust high, 100For businessesPrompt SecurityMake it safe · Prompt Security (SentinelOne)See which AI your team uses and protect your dataPaidTrust high, 100For businessesReality DefenderMake it safe · Reality Defender Inc.Detect deepfakes in voice, images and videoFree versionTrust high, 100Beginner-friendlySensityMake it safe · SensityHave suspicious media examined forensicallyPaidTrust high, 100For businessesTrojAIMake it safe · TrojAI (A10 Networks)Test AI models and monitor agent trafficPaidTrust high, 100For businessesZenityMake it safe · ZenityDecide what your AI agents are allowed to doPaidTrust high, 100For businessesAktoMake it safe · AktoFind and test MCP servers and APIs in your companyOpen SourceTrust high, 97For developersLasso SecurityMake it safe · Lasso SecurityKeep an eye on your own AI apps and agentsPaidTrust high, 92For businessesNoma SecurityMake it safe · Noma SecurityVisibility and control over all your AI agentsPaidTrust high, 92For businessesPillar SecurityMake it safe · Pillar SecurityFind, test and protect every AI componentPaidTrust high, 92For businessesPrisma AIRSMake it safe · Palo Alto NetworksSecure AI models, apps and agents with one vendorPaidTrust high, 92For businessesSocketMake it safe · SocketStop malicious packages before they reach your codeFree versionLimited checks · 2 checksFor developers