Protect AI
Protect AI is an AI/ML security company building defensive tooling and open-source security research for the model supply chain, large language model (LLM) applications, and runtime AI workloads. The commercial platform is anchored by three products — Guardian (AI model security and third-party model scanning across PyTorch, TensorFlow, ONNX, Keras, Pickle, GGUF, Safetensors, and 35+ formats with Hugging Face, SageMaker, MLflow, S3, Git, and Artifactory integrations), Recon (scalable AI red teaming with an attack library of 450+ known attacks against LLM applications mapped to OWASP LLM Top 10), and Layer (runtime AI security with 27 turnkey policies, eBPF and SDK collection, and DataDog/Splunk/Elastic/PagerDuty integration). Protect AI also stewards a portfolio of widely used open-source AI security projects on GitHub including LLM Guard (input/output scanner toolkit for prompt injection, PII, toxicity, secrets, and data leakage detection), ModelScan (model serialization attack scanner), Rebuff (prompt injection detector, archived May 2025), NB Defense (Jupyter notebook security), AI Exploits (real-world AI/ML vulnerability demonstrations), and Vulnhuntr (LLM-driven autonomous vulnerability discovery), plus the huntr bug bounty platform for AI/ML with over 17,000 security researchers. Protect AI was acquired by Palo Alto Networks in 2025 and is being integrated into the Prisma AIRS AI security platform. No public, programmatic developer API or OpenAPI specification is published for Guardian, Recon, or Layer at the time of this profile — integration is performed via product CLIs, SDKs, eBPF agents, and platform connectors documented behind Palo Alto Networks customer accounts.
Index entry only — little beyond a description and a link, and nothing machine-readable enough for an agent to act on without a human reading the site first.
API Evangelist profiles Protect AI the way a machine reads it — 1 machine-readable artifact, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Protect AI scores 9.6/100 (minimal), with a separate agent-readiness read of 0/100 (human only). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile Protect AI
Each block below is one kind of artifact we hold for Protect AI. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
Security Posture 1
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Resources
Every other property we hold for Protect AI — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Documentation 2
Reference material describing how the API behaves
Build 1
SDKs, sample code, and the tooling you integrate with
Access & Security 2
Authentication, authorization, and security posture
Learn 2
Tutorials, courses, talks, and written guidance
Company 5
The organization behind the API
Other 11
Properties that don't map to a standard resource type
Scroll within the panel for all 11 ·
← All providers · Data indexed from github.com/api-evangelist/protect-ai · machine-readable index on apis.io