Sweet AI Security Platform

Visit official site ↗

Overview

Product details compiled from public sources, each with a citation.

Vendor
Sweet Security2
Description
Runtime detection and response for AI systems that inventories models and agents, blocks prompt injection through an AI gateway, and enforces least privilege for agents.2
Deployment
SaaS1
Status
Active3

Matrix Coverage

Where this product defends, by asset class and NIST CSF function. The Coverage column shows whether each asset is Primary, Secondary, or Adjacent to what the product does. The table omits empty rows and columns.

Asset class IdentifyProtectDetect Coverage Source
AI Model Protect: Not covered Detect: Not covered Secondary 2
Runtime AI Data Identify: Not covered Primary 2
AI Agent Identities Detect: Not covered Primary 2

Framework Relevance

These frameworks include controls relevant to the asset classes Sweet AI Security Platform defends. This is an editorial inference from the AI Defense Matrix asset-level crossmap, not a statement that Sweet Security implements these controls or is certified against them.

Expand Collapse
Framework Asset class Relevant controls
NIST IR 8596 AI Model Models; Algorithms (model configuration)
Runtime AI Data Prompts (runtime); inference data
AI Agent Identities Agents as autonomous principals; Keys; Integrations and permissions
CSA AI Controls Matrix AI Model Model Security; Governance, Risk and Compliance
Runtime AI Data Data Security and Privacy Lifecycle Management; Application and Interface Security
AI Agent Identities IAM; Governance, Risk and Compliance
ISO 42001 AI Model A.6 AI system life cycle; A.10 Third-party and customer relationships; A.5 Assessing impacts of AI systems
Runtime AI Data A.7 Data for AI systems; A.8 Information for interested parties
AI Agent Identities A.9 Use of AI systems; A.3 Internal organization; A.5 Assessing impacts of AI systems
Google SAIF AI Model Protect the AI model; ensure model integrity, provenance, and weight security
Runtime AI Data Expand AI red-teaming; runtime input and output safety; prompt defense
AI Agent Identities Focus on Agents (explicit SAIF section); identity, authorization, and delegation controls
SANS Critical AI Security Guidelines AI Model Conventional Security Controls (protect model parameters with least privilege, encryption at rest, runtime obfuscation, and trusted execution environments); Data/Model Engineering Controls (adversarial training; alignment and fine-tuning); AI Supply Chain Management (public-model caution; transfer-attack exposure)
Runtime AI Data Model I/O Handling (sanitize, validate, and filter inputs and outputs; segregate user and system prompts; multilayered prompt-injection defense); Conventional Security Controls (protect augmentation and RAG data with vector-store access controls and validation); Data Minimization and Obfuscation (limit sensitive prompt content; context-window management); Limit Model Behavior (AI guardrails)
AI Agent Identities Secure Agentic Systems and AI Autonomy Controls (defined function scope; API and function-call gating; escalation and fallback); Limit Model Behavior (least-privilege focused functionality; human oversight; override capabilities)
MITRE ATLAS AI Model AML.T0043 Craft Adversarial Data; AML.T0024 Exfiltration via AI Inference API (subtechniques: AML.T0024.001 Invert AI Model and AML.T0024.002 Extract AI Model); AML.T0018 Manipulate AI Model (integrity and backdoor)
Runtime AI Data AML.T0051 LLM Prompt Injection; AML.T0054 LLM Jailbreak; AML.T0056 Extract LLM System Prompt
AI Agent Identities AML.T0053 AI Agent Tool Invocation; credential and delegation-chain abuse
OWASP AI Exchange AI Model Development-time and runtime model threats: model inversion, extraction, evasion, poisoning
Runtime AI Data Input threats: prompt injection, adversarial inputs, evasion; runtime threats: RAG poisoning, memory tampering
AI Agent Identities Runtime threats: unauthorized agent actions, capability abuse, delegation chain exploitation
OWASP LLM Top 10 AI Model LLM03 Supply Chain; LLM04 Data and Model Poisoning; LLM09 Misinformation
Runtime AI Data LLM01 Prompt Injection; LLM02 Sensitive Information Disclosure; LLM08 Vector and Embedding Weaknesses; LLM05 Improper Output Handling
AI Agent Identities LLM06 Excessive Agency; LLM05 Improper Output Handling; unauthorized actions by AI agents
OWASP Agentic Security Top 10 AI Model ASI04 Agentic Supply Chain Vulnerabilities (model provenance, weights, and dynamic loading)
Runtime AI Data ASI06 Memory & Context Poisoning; ASI01 Agent Goal Hijack (via prompt injection in runtime inputs)
AI Agent Identities ASI03 Identity and Privilege Abuse; ASI10 Rogue Agents; ASI09 Human-Agent Trust Exploitation; ASI02 Tool Misuse and Exploitation (when tied to agent permissions)

Provenance

Last sourced 2026-06-10.

Expand Collapse

Sources

  1. Sweet Security Suite listing on AWS Marketplace
    Vendor source accessed 2026-06-10
  2. Sweet AI Security Platform product page
    Vendor source accessed 2026-06-10
    • “Through its unified platform, Sweet ensures continuous visibility, provides runtime intelligence, and empowers policy-based control that ensures guardrails and allows AI developers to innovate fast.”
    • “Solution Sweet delivers full-lifecycle AI security from the level of the language model to agent execution in production systems.”
  3. Sweet Security Series B press release
    Vendor source accessed 2026-06-10

Changelog

  1. Added to the catalog from the Sweet Security documentation.

Found an error? Corrections are welcome. Suggest an edit.