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.
Holistic AI
AI governance platform for inventorying models, assessing risk against regulatory frameworks and running bias audits on automated decision systems.
Guardrails AI
Python framework that wraps LLM calls in composable validators and decides what to do when a prompt or a response fails one.
Galileo
Evaluation and observability platform for LLM and agent applications, with purpose built scoring models and an inline guardrail path.
WhyLabs
Observability platform for ML and LLM systems built on lightweight statistical profiles, with drift monitoring and text quality and safety metrics.
Straiker
Commercial AI security platform pairing automated adversarial testing of AI applications with runtime inspection of prompts and responses.
Tencent
Open source scanner that fingerprints self hosted AI infrastructure components and matches them against known vulnerabilities, with an MCP server analysis mode.
Promptfoo
Config driven test and red team harness for LLM applications, running assertions and generated adversarial probes against prompts, models and agents.
Future AGI
Evaluation and observability platform for LLM applications, combining offline scoring of model output with runtime checks on inputs and responses.
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.
Cerbos
Decoupled authorization engine that evaluates YAML policies over a principal, resource and action and returns an allow or deny decision over an API.
Linux Foundation AI & Data
Python library implementing adversarial attacks and defenses against machine learning models, covering evasion, poisoning, extraction and inference.
NeuralTrust
AI gateway that inspects and enforces policy on LLM traffic, paired with adversarial testing and conversation observability.
Holistic AI
AI governance platform for inventorying models, assessing risk against regulatory frameworks and running bias audits on automated decision systems.
Guardrails AI
Python framework that wraps LLM calls in composable validators and decides what to do when a prompt or a response fails one.
Galileo
Evaluation and observability platform for LLM and agent applications, with purpose built scoring models and an inline guardrail path.
WhyLabs
Observability platform for ML and LLM systems built on lightweight statistical profiles, with drift monitoring and text quality and safety metrics.
Straiker
Commercial AI security platform pairing automated adversarial testing of AI applications with runtime inspection of prompts and responses.
Tencent
Open source scanner that fingerprints self hosted AI infrastructure components and matches them against known vulnerabilities, with an MCP server analysis mode.
Promptfoo
Config driven test and red team harness for LLM applications, running assertions and generated adversarial probes against prompts, models and agents.
Future AGI
Evaluation and observability platform for LLM applications, combining offline scoring of model output with runtime checks on inputs and responses.
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.
Cerbos
Decoupled authorization engine that evaluates YAML policies over a principal, resource and action and returns an allow or deny decision over an API.
Linux Foundation AI & Data
Python library implementing adversarial attacks and defenses against machine learning models, covering evasion, poisoning, extraction and inference.
NeuralTrust
AI gateway that inspects and enforces policy on LLM traffic, paired with adversarial testing and conversation observability.
Mindgard
Runs a library of AI attacks against your deployed models through their normal interface and reports which ones succeeded.
Lasso Security
GenAI security platform covering discovery of AI tools in use, inspection of prompts and responses, and controls on what data reaches a model.
Knostic
Detects where enterprise AI assistants expose data users should not reach, and maps the permission mistakes behind each exposure.
Giskard
Python testing library that scans models and LLM applications for security and quality failures, then turns findings into a reusable test suite.
Cylake
Commercial platform in the AI security category, offered as a hosted service.
Xage Security
Distributed zero trust access platform for operational and industrial environments, extended to control what machine and AI agent identities may do.
Akto
API security platform that builds an API inventory from mirrored traffic and runs automated tests for authorization, injection and data exposure flaws.
Protecto
Data privacy layer for AI pipelines that identifies sensitive fields in text and substitutes tokens so models never see the underlying values.
OpenAI
Open-source Python package that runs a configured pipeline of safety checks on prompts and model responses, tripping on policy violations.
Noma Security
AI security posture management that inventories models, pipelines and agents, scores their risk, and watches them at runtime.
NVIDIA
Command line LLM vulnerability scanner that fires a library of attack probes at a model endpoint and scores the responses with matched detectors.
WitnessAI
Governance platform that observes AI traffic across an organization, discovers unsanctioned tool use, and applies policy to prompts and responses.
Mindgard
Runs a library of AI attacks against your deployed models through their normal interface and reports which ones succeeded.
Lasso Security
GenAI security platform covering discovery of AI tools in use, inspection of prompts and responses, and controls on what data reaches a model.
Knostic
Detects where enterprise AI assistants expose data users should not reach, and maps the permission mistakes behind each exposure.
Giskard
Python testing library that scans models and LLM applications for security and quality failures, then turns findings into a reusable test suite.
Cylake
Commercial platform in the AI security category, offered as a hosted service.
Xage Security
Distributed zero trust access platform for operational and industrial environments, extended to control what machine and AI agent identities may do.
Akto
API security platform that builds an API inventory from mirrored traffic and runs automated tests for authorization, injection and data exposure flaws.
Protecto
Data privacy layer for AI pipelines that identifies sensitive fields in text and substitutes tokens so models never see the underlying values.
OpenAI
Open-source Python package that runs a configured pipeline of safety checks on prompts and model responses, tripping on policy violations.
Noma Security
AI security posture management that inventories models, pipelines and agents, scores their risk, and watches them at runtime.
NVIDIA
Command line LLM vulnerability scanner that fires a library of attack probes at a model endpoint and scores the responses with matched detectors.
WitnessAI
Governance platform that observes AI traffic across an organization, discovers unsanctioned tool use, and applies policy to prompts and responses.