Agent Access Restriction
Specification
Restrict agents' access to the tools and plugins necessary for the activity or use case at hand, ensuring adherence to the principles of need-to-know and least privilege.
Threat coverage
Architectural relevance
Lifecycle
Not applicable
Design, Guardrails
Validation/Red Teaming
Orchestration, AI applications
Operations, Continuous monitoring
Not applicable
Ownership / SSRM
PI
Shared Cloud Service Provider-Model Provider (Shared CSP-MP)
The CSP and MP are jointly responsible and accountable for the design, development, implementation, and enforcement of the control to mitigate security, privacy, or compliance risks associated with Large Language Model (LLM)/GenAI technologies in the context of the services or products they develop and offer.
Model
Owned by the Model Provider (MP)
The model provider (MP) designs, develops, and implements the control as part of their services or products to mitigate security, privacy, or compliance risks associated with the Large Language Model (LLM). Model Providers are entities that develop, train, and distribute foundational and fine-tuned AI models for various applications. They create the underlying AI capabilities that other actors build upon. Model Providers are responsible for model architecture, training methodologies, performance characteristics, and documentation of capabilities and limitations. They operate at the foundation layer of the AI stack and may provide direct API access to their models. Examples: OpenAI (GPT, DALL-E, Whisper), Anthropic(Claude), Google(Gemini), Meta(Llama), as well as any customized model.
Orchestrated
Shared Orchestrated Service Provider-Application Provider (Shared OSP-AP)
The OSP and AP are jointly responsible and accountable for the design, development, implementation, and enforcement of the control to mitigate security, privacy, or compliance risks associated with Large Language Model (LLM)/GenAI technologies in the context of the services or products they develop and offer.
Application
Owned by the Application Provider (AP)
The Application Provider (AP) is responsible for the design, development, implementation, and enforcement of the control to mitigate security, privacy, or compliance risks associated with Large Language Model (LLM)/GenAI technologies in the context of the services or products they develop and offer. The AP is responsible and accountable for the implementation of the control within its own infrastructure/environment. If the control has downstream implications on the users/customers, the AP is responsible for enabling the customer and/or upstream partner in the implementation/configuration of the control within their risk management approach. The AP is accountable for carrying out the due diligence on its upstream providers (e.g MPs, Orchestrated Services) to verify that they implement the control as it relates to the service/product develop and offered by the AP. These providers build and offer end-user applications that leverage generative AI models for specific tasks such as content creation, chatbots, code generation, and enterprise automation. These applications are often delivered as software-as-a-service (SaaS) solutions. These providers focus on user interfaces, application logic, domain-specific functionality, and overall user experience rather than underlying model development. Example: OpenAI (GPTs,Assistants), Zapier, CustomGPT, Microsoft Copilot (integrated into Office products), Jasper (AI-driven content generation), Notion AI (AI-enhanced productivity tools), Adobe Firefly (AI-generated media), and AI-powered customer service solutions like Amazon Rufus, as well as any organization that develops its AI-based application internally.
Implementation guidelines
Auditing guidelines
1. Verify that consent and identity mapping services offered by CSPs are compliant with privacy frameworks. 2. Confirm support for federated identity systems enabling cross-platform consent synchronization. 3. Validate revocation propagation across CSP-hosted microservices or serverless architectures. 4. Ensure CSP logging infrastructure retains mappings only as long as necessary. 5. Confirm service-level agreements support customer demands for identity mapping transparency.
Standards mappings
27001: A.5.15 — Access Control Policy 27001: A.5.18 — Access Rights 27002: 8.1 – User Access Management 27002: 8.2 – Privileged Access Rights 27002: 8.3 – Information Access Restriction 27002: 5.15 – Segregation of Duties 42001: 8.5 – Operational Control of AI Systems 42001: 8.6 – AI System Access Control 42001: 6.2 – Risk Identification for AI
Addendum
N/A
No Mapping
Addendum
Require: Enforcing least privilege and need-to-know principles when granting access to AI systems and their components, restricting agent access to only the tools/plugins required for their specific activity/use case, and documenting access controls and policies as part of the technical documentation.
No Mapping
Addendum
Does not include operational access control requirements.
C4 DM-01 DM-02
Addendum
No specific handling rules for agent based solutions or api for this kind of software in AIC4.
AI-CAIQ questions (1)
Are agents' access to the tools and plugins necessary for the activity or use case at hand, restricted to ensure adherence to the principles of need-to-know and least privilege?