AI Security
Test and defend models, prompts, agents and the infrastructure around them.
45 tools profiled
How it differs Tests and guards models, LLM applications and agents against prompt injection, jailbreaks and data leakage. Scanning an AI app's own code is still SAST or SCA.
7AI
Platform that applies AI agents to security operations work such as alert triage, phishing analysis and exposure investigation.
Linux Foundation AI & Data
Python library implementing adversarial attacks and defenses against machine learning models, covering evasion, poisoning, extraction and inference.
SplxAI
Open source CLI that statically analyzes agentic AI codebases and produces a visual map of agents, their tools and the risks in that wiring.
Tencent
Open source scanner that fingerprints self hosted AI infrastructure components and matches them against known vulnerabilities, with an MCP server analysis mode.
Akto
API security platform that builds an API inventory from mirrored traffic and runs automated tests for authorization, injection and data exposure flaws.
Alter
Commercial product in the AI security category addressing identity and access control for AI agents.
Arize AI
LLM and ML observability platform that captures application traces and runs evaluations over them, with an open source tracing and evaluation component.
Arthur
Model monitoring and guardrail platform that evaluates LLM inputs and outputs inline for injection, sensitive data and unsupported claims.
Praetorian
Open source prompt injection testing tool released by Praetorian for probing LLM applications with adversarial inputs.
CalypsoAI
Commercial platform that proxies enterprise LLM traffic through policy scanners and runs automated red teaming against models and applications.
Cerbos
Decoupled authorization engine that evaluates YAML policies over a principal, resource and action and returns an allow or deny decision over an API.
Cisco
Open source project from Cisco's AI Defense group addressing security controls for AI agent and LLM application activity.
7AI
Platform that applies AI agents to security operations work such as alert triage, phishing analysis and exposure investigation.
Linux Foundation AI & Data
Python library implementing adversarial attacks and defenses against machine learning models, covering evasion, poisoning, extraction and inference.
SplxAI
Open source CLI that statically analyzes agentic AI codebases and produces a visual map of agents, their tools and the risks in that wiring.
Tencent
Open source scanner that fingerprints self hosted AI infrastructure components and matches them against known vulnerabilities, with an MCP server analysis mode.
Akto
API security platform that builds an API inventory from mirrored traffic and runs automated tests for authorization, injection and data exposure flaws.
Alter
Commercial product in the AI security category addressing identity and access control for AI agents.
Arize AI
LLM and ML observability platform that captures application traces and runs evaluations over them, with an open source tracing and evaluation component.
Arthur
Model monitoring and guardrail platform that evaluates LLM inputs and outputs inline for injection, sensitive data and unsupported claims.
Praetorian
Open source prompt injection testing tool released by Praetorian for probing LLM applications with adversarial inputs.
CalypsoAI
Commercial platform that proxies enterprise LLM traffic through policy scanners and runs automated red teaming against models and applications.
Cerbos
Decoupled authorization engine that evaluates YAML policies over a principal, resource and action and returns an allow or deny decision over an API.
Cisco
Open source project from Cisco's AI Defense group addressing security controls for AI agent and LLM application activity.
CrowdStrike
AI detection and response module on the Falcon platform that discovers AI tools, models and libraries in use and detects threats against them.
Cylake
Commercial platform in the AI security category, offered as a hosted service.
Confident AI
Open source Python framework that generates adversarial prompts against an LLM application and scores the responses for vulnerabilities such as bias, PII leakage and excessive agency.
Future AGI
Evaluation and observability platform for LLM applications, combining offline scoring of model output with runtime checks on inputs and responses.
CyberArk
Open source fuzzer that applies a catalog of published jailbreak and prompt injection techniques against local or hosted language model endpoints.
Galileo
Evaluation and observability platform for LLM and agent applications, with purpose built scoring models and an inline guardrail path.
NVIDIA
Command line LLM vulnerability scanner that fires a library of attack probes at a model endpoint and scores the responses with matched detectors.
Giskard
Python testing library that scans models and LLM applications for security and quality failures, then turns findings into a reusable test suite.
Guardrails AI
Python framework that wraps LLM calls in composable validators and decides what to do when a prompt or a response fails one.
HiddenLayer
Commercial platform that scans serialized model files for embedded code and watches inference traffic for extraction and evasion behavior.
Holistic AI
AI governance platform for inventorying models, assessing risk against regulatory frameworks and running bias audits on automated decision systems.
Knostic
Detects where enterprise AI assistants expose data users should not reach, and maps the permission mistakes behind each exposure.
CrowdStrike
AI detection and response module on the Falcon platform that discovers AI tools, models and libraries in use and detects threats against them.
Cylake
Commercial platform in the AI security category, offered as a hosted service.
Confident AI
Open source Python framework that generates adversarial prompts against an LLM application and scores the responses for vulnerabilities such as bias, PII leakage and excessive agency.
Future AGI
Evaluation and observability platform for LLM applications, combining offline scoring of model output with runtime checks on inputs and responses.
CyberArk
Open source fuzzer that applies a catalog of published jailbreak and prompt injection techniques against local or hosted language model endpoints.
Galileo
Evaluation and observability platform for LLM and agent applications, with purpose built scoring models and an inline guardrail path.
NVIDIA
Command line LLM vulnerability scanner that fires a library of attack probes at a model endpoint and scores the responses with matched detectors.
Giskard
Python testing library that scans models and LLM applications for security and quality failures, then turns findings into a reusable test suite.
Guardrails AI
Python framework that wraps LLM calls in composable validators and decides what to do when a prompt or a response fails one.
HiddenLayer
Commercial platform that scans serialized model files for embedded code and watches inference traffic for extraction and evasion behavior.
Holistic AI
AI governance platform for inventorying models, assessing risk against regulatory frameworks and running bias audits on automated decision systems.
Knostic
Detects where enterprise AI assistants expose data users should not reach, and maps the permission mistakes behind each exposure.