Back to library

Security and safeguards

Practical safeguards, threat modeling, and secure development guidance for agentic systems.

11 resources

Type:
11 resources found
frameworkGoogle • 2025

Secure AI Framework (SAIF) 2.0: Focus on Agents

Google's Secure AI Framework v2 extends SAIF's six security principles to agents, adding risk maps for autonomy, tool permissions, memory poisoning, and multi-agent interactions. Includes a self-assessment and a risk-control matrix for agent developers.

Secure development frameworksGlobal
researchChristoph Kern, Kara Olive (Google) • 2025

Google's Approach for Secure AI Agents

Kern and Olive (Google) outline Google's hybrid approach to agent security combining traditional AppSec controls with LLM-specific defences. Covers isolation, least-privilege tool access, prompt-injection mitigations, and runtime monitoring in Google's internal agent deployments.

Secure development frameworksGlobal
guidelineCyber Security Agency of Singapore • 2025

Securing Agentic AI: An Addendum to the Guidelines and Companion Guide on Securing AI Systems

Cyber Security Agency of Singapore addendum updating its AI systems guidelines for agentic use cases. Adds controls for autonomy boundaries, tool vetting, inter-agent communication, and incident response, aligned with the Companion Guide.

Secure development frameworksSingapore
reportCSA Singapore and FAR.AI • 2025

Securing Agentic AI: A Discussion Paper

CSA Singapore and FAR.AI joint discussion paper classifying threats to agentic AI across adversarial, misuse, and systemic categories. Proposes layered controls covering model training, deployment guardrails, and runtime monitoring, with worked examples.

Threat modelingSingapore
guidelineMcKinsey • 2025

Deploying agentic AI with safety and security: A playbook for technology leaders

McKinsey playbook for technology leaders deploying agents safely, covering governance operating model, guardrail layers (input, model, tool, output), evaluation cadence, and incident response. Includes a maturity assessment and reference architecture.

Runtime safeguardsGlobal
guidelineMeta • 2025

Agents Rule of Two: A Practical Approach to AI Agent Security

Meta's heuristic constraining agents to at most two of: processing untrusted inputs, accessing sensitive systems, and taking unconfirmed actions. Frames the rule as a practical bound on blast radius until prompt-injection defences mature.

Runtime safeguardsGlobal
guidelineOWASP • 2025

Multi-Agentic System Threat Modelling Guide v1.0

OWASP v1.0 threat modelling guide for multi-agent generative AI systems, covering trust boundaries between agents, memory-sharing risks, orchestration attacks, and collusion. Walks through STRIDE-style analysis applied to a reference multi-agent architecture.

Threat modelingInternational
guidelineOWASP • 2025

Agentic AI - Threats and Mitigations

OWASP catalogue of agentic AI threats paired with technical and procedural mitigations, organised by attack vector (planning, memory, tools, outputs, identity). Companion reference to the OWASP Top 10 for Agentic Applications with deeper control detail.

Threat modelingInternational
standardNIST • 2026

AI Agent Standards Initiative for Interoperable and Secure Innovation

NIST announcement of a cross-industry initiative to develop standards for interoperable and secure AI agents, covering identity, capability declaration, audit logs, and evaluation. Coordinates with CAISI, industry partners, and international standards bodies.

Secure development frameworksUnited States
guidelineFederal Office for Information Security (BSI), Germany • 2024

Generative AI Models – Opportunities and Risks for Industry and Authorities

Germany's Federal Office for Information Security overview of generative AI opportunities and risks, with security recommendations for procurement, development, and deployment. Covers data leakage, prompt injection, and supply-chain risks relevant to agent builders.

Secure development frameworksGermany
guidelineANSSI (France) • 2025

Intelligence artificielle — ANSSI

France's ANSSI cybersecurity agency hub for AI guidance, bringing together its recommendations on securing generative AI deployments, supply-chain risks, and state-actor threats, including emerging considerations for agentic workflows.

Secure development frameworksFrance
Security and safeguards | VerifyWise AI Governance Library