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 | Protect | Detect | Respond | Coverage | Source |
|---|---|---|---|---|---|
| AI Traffic | Detect: Not covered | Respond: Not covered | Primary | 1 | |
| Runtime AI Data | Respond: Not covered | Secondary | 4 | ||
| AI Agent Identities | Detect: Not covered | Secondary | 2 |
Framework Relevance
These frameworks include controls relevant to the asset classes Keel defends. This is an editorial inference from the AI Defense Matrix asset-level crossmap, not a statement that Keel implements these controls or is certified against them.
Expand Collapse
| Framework | Asset class | Relevant controls |
|---|---|---|
| NIST IR 8596 | AI Traffic | AI data flows; APIs; inference endpoints (traffic side); model registries and dataset sources |
| Runtime AI Data | Prompts (runtime); inference data | |
| AI Agent Identities | Agents as autonomous principals; Keys; Integrations and permissions | |
| CSA AI Controls Matrix | AI Traffic | Infrastructure Security; Interoperability and Portability |
| Runtime AI Data | Data Security and Privacy Lifecycle Management; Application and Interface Security | |
| AI Agent Identities | IAM; Governance, Risk and Compliance | |
| ISO 42001 | AI Traffic | A.8 Information for interested parties; A.9 Use of AI systems; A.10 Third-party and customer relationships |
| 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 Traffic | Harden and monitor infrastructure; network-level access and egress controls |
| 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 Traffic | Conventional Security Controls (authenticate and control access to inference APIs; API key management); Model I/O Handling (rate limiting; egress output filtering); Monitoring (interaction and API-usage logging) |
| 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 Traffic | AML.T0057 LLM Data Leakage; AML.T0024 Exfiltration via AI Inference API (network-side observation) |
| 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) | |
| AI Agent Identities | AML.T0053 AI Agent Tool Invocation; credential and delegation-chain abuse | |
| OWASP AI Exchange | AI Traffic | Runtime threats: data leakage via AI egress; network-level access control gaps |
| 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 Traffic | LLM10 Unbounded Consumption (cost and rate control); shadow AI egress and output handling |
| 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 Traffic | ASI07 Insecure Inter-Agent Communication; ASI02 Tool Misuse and Exploitation (egress and tool-invocation scope); ASI04 Agentic Supply Chain Vulnerabilities (MCP and tool-registry trust) |
| 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 2026-10-31.
Expand Collapse
Sources
- Keel documentation
- “It evaluates policy, budget, routing, delegation and approval before dispatching supported actions, records the result in an AI Permit, and produces route-appropriate evidence for later review.”
- Keel agent verification documentation
- “An Authority runtime key is a project API key bound to one specific Agent principal.”
- Keel egress-controlled deployments documentation
- Keel prompt firewall documentation
- “The Prompt Firewall is a route-attached inspection layer that scans request payloads for sensitive text and metadata before any provider call.”
- Keel pricing
Changelog
-
Added to the catalog from the Keel website and documentation.
Found an error? Corrections are welcome. Suggest an edit.