17.9
PromptGuard is a security layer between an application and its LLM provider that inspects requests before they reach the model.
Free planWebAPIExtension
Alternatives to OpenSecureAI Scanner
OpenSecureAI Scanner is a focused option for checking untrusted text for prompt injection, jailbreaks, system-prompt leaks, and data-exfiltration patterns. Its scanPrompt API returns a score, risk level, and per-rule findings; developers can also use an npm package, CLI, GitHub Action, or REST API. Authenticated hosted scans add detections for obfuscation, indirect injection, tool abuse, multilingual overrides, and de-obfuscation. The LLM Gateway can route prompts to…
27.8
Promptfoo helps developers and enterprises evaluate prompts and test AI applications for security risks.
Free planOpen sourceWebAPILinux
37.6
Giskard is a freemium platform for finding security and quality problems in AI agents before production use.
Free planOpen sourceWebAPILinux
- 4
AIRTA Red Team
AIRTA Red Team is a self-hosted tool for authorized adversarial assessments of LLMs and LLM-driven applications.
Free planOpen sourceWebAPILinuxmacOS7.5Free plan - 5
CyberSecEval
CyberSecEval 4 is a free benchmark suite for assessing cybersecurity vulnerabilities and defensive capabilities in large language models.
Free planOpen sourceWebAPILinuxmacOS7.5Free plan - 6
Project Moonshot
Project Moonshot is an open-source toolkit for assessing the safety and reliability of large language models and AI applications.
Free planWebAPILinuxmacOS6.9Free plan - 7
AgentScan
AgentScan is a cloud service that provides automated security testing for LLMs, retrieval-augmented generation pipelines, and autonomous agents through an API.
Free planWebAPI6.7From $29 a month - 8
PyRIT
PyRIT is a free, open-source framework for automated and human-led red teaming of generative AI systems, aimed at assessing security and safety.
Free planWebAPILinuxmacOS6.3Free plan - 9
garak
garak is a free, open-source command-line scanner for security weaknesses in language models and systems that use them.
Free planLinuxmacOSSelf-hostedWindows6.2Free plan - 10
Augustus
Augustus is a Go-based vulnerability scanner for security professionals assessing large language models.
Free planLinuxmacOSSelf-hostedWindows6.1Free plan - 11
Basilisk
Basilisk is an open-source framework for authorized security testing, vulnerability research, and academic study of AI and LLM systems.
Free planLinuxmacOSWindows6.1Free plan - 12
RedForge
RedForge is a free, open-source platform for red teaming and vulnerability scanning of large language models.
Free planAPILinuxSelf-hosted6.1Free plan - 13
AIRTaaS
AIRTaaS is a web platform for ongoing security testing and validation of agentic AI applications, with a free plan listed as free.
Free planWeb6.0Free plan - 14
Mindgard
Mindgard is an AI security platform for discovering, assessing, and defending AI systems and agents.
WebAPIExtension5.9 - 15
Akto Agentic Red Teaming
Akto Agentic Red Teaming provides continuous adversarial testing for AI agents, copilots, retrieval-augmented generation systems, and AI-powered applications.
WebAPISelf-hosted5.8 - 16
Crucible
Crucible is a self-hosted security tool for stress-testing AI agents against attacks such as prompt injection, goal hijacking, and tool misuse before production.
Free planLinuxSelf-hosted5.8Free plan - 17
DeepTeam
DeepTeam is an open-source Python framework for red teaming large language model systems.
Free planAPISelf-hosted5.8Free plan - 18
LLMMap
LLMMap is a free, open-source Linux tool for authorized security testing of applications that use large language models.
Free planLinux5.8Free plan - 19
Prompt Security AI Red Teaming
Prompt Security AI Red Teaming is a paid AI security offering for organizations testing homegrown AI applications before release.
WebSelf-hosted5.7 - 20
PromptRAID
PromptRAID is a free, open-source, self-hosted command-line framework for red-teaming prompt injection in LLM agents.
LinuxWindows5.7 - 21
RAMPART
RAMPART is a free, open-source framework for writing and running safety and security tests for agentic AI applications.
APILinuxmacOSWindows5.7 - 22
SENTINEL RED
SENTINEL RED is a free, open-source suite for security and quality testing of applications built with large language models.
WebAPILinuxSelf-hosted5.5 - 23
AgentDojo
AgentDojo is a free, self-hosted environment for researchers evaluating prompt injection attacks and defenses for LLM agents.
APILinuxSelf-hosted5.4 - 24
HarmBench
APILinuxSelf-hosted5.4 - 25
SuperRed
SuperRed is a free, open-source Linux framework for red-teaming chatbots, agents, and assistants.
Linux5.4 - 26
Red Team LLM Lab
Self-hostedWindows5.3 - 275.1
- 284.5