AI Defense Matrix Catalog

Flint AI CLI

Visit official site

Overview

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

Vendor
SandboxAQ1agent · Details at Cyber Company Profiles
Description
Free local-first CLI that scans AI agent source code for risky tool access and missing guardrails and runs adversarial evals against running agents, with findings mapped to OWASP ASI.2agent
Deployment
Self-hosted2agent
Status
Active2agent

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 Detect Coverage
AI Coding and Orchestration Tools Primary 2
Runtime AI Data Secondary 2

Framework Relevance

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

Expand Collapse
Framework Asset class Relevant controls
NIST IR 8596 AI Coding and Orchestration Tools Agents as deployed artifacts (orchestration view; see AI Agent Identities row for the principal view); system prompts and templates
Runtime AI Data Prompts (runtime); inference data
CSA AI Controls Matrix AI Coding and Orchestration Tools Application and Interface Security; Supply Chain Management
Runtime AI Data Data Security and Privacy Lifecycle Management; Application and Interface Security
ISO 42001 AI Coding and Orchestration Tools A.6 AI system life cycle; A.5 Assessing impacts of AI systems
Runtime AI Data A.7 Data for AI systems; A.8 Information for interested parties
Google SAIF AI Coding and Orchestration Tools Secure the AI supply chain; application and pipeline security; agent orchestration controls
Runtime AI Data Expand AI red-teaming; runtime input and output safety; prompt defense
SANS Critical AI Security Guidelines AI Coding and Orchestration Tools Secure Agentic Systems and AI Autonomy Controls (defined function scope; execution isolation; API and function-call gating); Limit Model Behavior (focused functionality; access controls outside the model)
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)
MITRE ATLAS AI Coding and Orchestration Tools AML.T0051 LLM Prompt Injection; AML.T0054 LLM Jailbreak; AML.T0016 Obtain Capabilities (malicious plugins)
Runtime AI Data AML.T0051 LLM Prompt Injection; AML.T0054 LLM Jailbreak; AML.T0056 Extract LLM System Prompt (system prompt leaks as inference data; the AI Coding and Orchestration Tools row owns it as configuration)
OWASP AI Exchange AI Coding and Orchestration Tools Development-time threats: agent framework supply chain; runtime threats: plugin abuse, prompt injection via tools
Runtime AI Data Input threats: prompt injection, adversarial inputs, evasion; runtime threats: RAG poisoning, memory tampering
OWASP LLM Top 10 AI Coding and Orchestration Tools LLM01 Prompt Injection; LLM05 Improper Output Handling; LLM07 System Prompt Leakage; LLM10 Unbounded Consumption
Runtime AI Data LLM01 Prompt Injection; LLM02 Sensitive Information Disclosure; LLM08 Vector and Embedding Weaknesses; LLM05 Improper Output Handling
OWASP Agentic Security Top 10 AI Coding and Orchestration Tools ASI01 Agent Goal Hijack; ASI02 Tool Misuse and Exploitation; ASI05 Unexpected Code Execution (RCE); ASI07 Insecure Inter-Agent Communication; ASI08 Cascading Failures; ASI10 Rogue Agents
Runtime AI Data ASI06 Memory & Context Poisoning; ASI01 Agent Goal Hijack (via prompt injection in runtime inputs)

Provenance

Last sourced 2026-10-05.

Expand Collapse

Sources

  1. About Flint AI
    Vendor source accessed 2026-10-05
  2. Flint AI CLI
    Vendor source accessed 2026-10-05
    • “Find misconfigurations, risky tool access, missing guardrails, and other issues in your Python agent code.”
    • “flintai eval sends adversarial and functional prompts to your running agent and scores the responses.”

Changelog

  1. Updated source links to the vendor’s new domain.

  2. Refreshed source links and quotes against the current vendor pages.

  3. Added to the catalog from the Flint AI CLI documentation, scoped to the CLI (the vendor lists a separate Platform as coming soon).

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