Cyberhaven AI Security
Overview
Product details compiled from public sources, each with a citation.
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 | Identify | Protect | Detect | Coverage | Source |
|---|---|---|---|---|---|
| Runtime AI Data | Identify: Not covered | Secondary | 1 | ||
| AI Agent Identities | Protect: Not covered | Primary | 1 |
Framework Relevance
These frameworks include controls relevant to the asset classes Cyberhaven AI Security defends. This is an editorial inference from the AI Defense Matrix asset-level crossmap, not a statement that Cyberhaven implements these controls or is certified against them.
Expand Collapse
| Framework | Asset class | Relevant controls |
|---|---|---|
| NIST IR 8596 | Runtime AI Data | Prompts (runtime); inference data |
| AI Agent Identities | Agents as autonomous principals; Keys; Integrations and permissions | |
| CSA AI Controls Matrix | Runtime AI Data | Data Security and Privacy Lifecycle Management; Application and Interface Security |
| AI Agent Identities | IAM; Governance, Risk and Compliance | |
| ISO 42001 | 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 | 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 | 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 | 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 | 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 | 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 | 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 2026-06-13.
Expand Collapse
Sources
- Cyberhaven AI Security
- “Cyberhaven uses an endpoint agent to continuously inventory AI tools as they appear across the organization, including mainstream SaaS generative AI applications, coding assistants running in IDEs and CLIs, open-source agent frameworks, and Model Context Protocol (MCP) servers.”
- “Cyberhaven can block, warn, or redact in real time based on data context and the risk score of the tool involved. Enforcement operates across the full agentic workflow, including prompts, responses, and downstream data flows.”
Changelog
-
Added to the catalog from the Cyberhaven AI Security documentation.
Found an error? Corrections are welcome. Suggest an edit.