Adversa AI

Adversa AI is an autonomous AI red-teaming and security company (founded 2021, Tel Aviv) that provides continuous security assessment for AI agents, LLMs, and GenAI applications. Its platform runs 300+ attack techniques — jailbreaks, prompt injection, and adversarial attacks — is OWASP- and NIST-mapped, runs its detection models on-prem so customer data is never exposed to external AI providers, and prioritizes every finding by real business impact with auto-generated remediation. Offerings include AI Threat Modelling, Continuous Security Assessment, Hardening & Remediation, and the AI Risk Quadrant (AIRQ) scoring framework. Adversa AI experts are co-leads and core members of NIST AI RMF, OWASP ASI, CoSAI, and CSA AI initiatives, and the company ships the open-source SecureClaw plugin/skill for hardening OpenClaw agents.

Adversa AI is profiled on the APIs.io network. Tagged areas include Company, Ai Security, AI Red Teaming, LLM Security, and Agentic AI.

Adversa AI’s developer surface includes engineering blog, signup flow, CLI, and 13 more developer resources.

🌐 Visit website 📡 Source on GitHub

19.7/100 emerging ▬ flat Agent 9/100 human only Full breakdown ↓
scored 2026-07-27 · rubric v0.5

0 APIs

CompanyAi SecurityAI Red TeamingLLM SecurityAgentic AIAdversarial Machine LearningAI GovernanceCybersecurity

Kin Score

Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5

Composite quality — 19.7/100 · emerging

Contract Quality 0.0 / 25

Developer Ergonomics 3.0 / 20

Commercial Clarity 7.9 / 20

Operational Transparency 2.1 / 13

Governance 0.0 / 12

Discoverability 6.8 / 10

Agent readiness — 9/100 · human only

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 15

MCP Server 0 / 12

Machine-Readable Auth 0 / 10

Idempotency 0 / 9

Stable Error Semantics 0 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 0 / 6

Agent Skills 5 / 5

Well-Known Catalog 4 / 4

Consent & Bot Identity 0 / 3

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/adversa-ai: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

Get Started 1

Portal, sign-up, and the first successful call

SignUp

SignUp

Agent Surfaces 3

MCP servers, agent skills, and machine-readable catalogs

AgentSkill

AgentSkill

LLMsTxt

LLMsTxt

WellKnown

WellKnown

Design & Contract 1

Pagination, idempotency, versioning, errors, and events

Conformance

Conformance

Build 3

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

GitHubOrganization

Packages

Packages

CLI

CLI

Access & Security 5

Authentication, authorization, and security posture

TrustCenter

TrustCenter

Compliance

Compliance

DomainSecurity

DomainSecurity

VulnerabilityDisclosure

VulnerabilityDisclosure

Security

Security

Commercial 1

Pricing, plans, and the legal terms of use

PrivacyPolicy

PrivacyPolicy

Company 2

The organization behind the API

Website

Website

Blog

Blog

Source (apis.yml)

aid: adversa-ai
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source: []
  generated: '2026-07-22'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/adversa-ai.png
name: Adversa AI
description: Adversa AI is an autonomous AI red-teaming and security company (founded 2021, Tel Aviv) that provides continuous
  security assessment for AI agents, LLMs, and GenAI applications. Its platform runs 300+ attack techniques — jailbreaks,
  prompt injection, and adversarial attacks — is OWASP- and NIST-mapped, runs its detection models on-prem so customer data
  is never exposed to external AI providers, and prioritizes every finding by real business impact with auto-generated remediation.
  Offerings include AI Threat Modelling, Continuous Security Assessment, Hardening & Remediation, and the AI Risk Quadrant
  (AIRQ) scoring framework. Adversa AI experts are co-leads and core members of NIST AI RMF, OWASP ASI, CoSAI, and CSA AI
  initiatives, and the company ships the open-source SecureClaw plugin/skill for hardening OpenClaw agents.
url: https://raw.githubusercontent.com/api-evangelist/adversa-ai/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- foundry-group
x-tier: stub
x-tier-reason: portfolio-lead
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-17'
tags:
- Company
- Ai Security
- AI Red Teaming
- LLM Security
- Agentic AI
- Adversarial Machine Learning
- AI Governance
- Cybersecurity
apis: []
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://adversa.ai
- type: Blog
  url: https://adversa.ai/topic/trusted-ai-blog/
- type: SignUp
  url: https://adversa.ai/get-demo/
- type: PrivacyPolicy
  url: https://adversa.ai/privacy-policy
- type: GitHubOrganization
  url: https://github.com/adversa-ai
- type: TrustCenter
  url: https://adversa.ai/security-trust/
- type: Compliance
  url: https://adversa.ai/security-trust/
- type: Packages
  url: packages/adversa-ai-packages.yml
- type: CLI
  url: cli/adversa-ai-cli.yml
- type: AgentSkill
  url: skills/_index.yml
- type: LLMsTxt
  url: llms/adversa-ai-llms.txt
- type: WellKnown
  url: well-known/adversa-ai-well-known.yml
- type: DomainSecurity
  url: security/adversa-ai-domain-security.yml
- type: VulnerabilityDisclosure
  url: security/adversa-ai-vulnerability-disclosure.yml
- type: Security
  url: security/adversa-ai-vulnerability-disclosure.yml
- type: Conformance
  url: conformance/adversa-ai-conformance.yml
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence

Adversa AI

Kin Score

Security Posture 3

Adversa Ai Domain Security

Adversa Ai Vulnerability Disclosure

Adversa Ai Trust Center

Resources