AI Agent Security

6 articles

Agent Security Agentic Permissions AI Agent Security AI Governance Evidence Ai Impact AI Incident Response Ai Integration AI Red Teaming AI SDLC & Product Security AI Security AI Security Engineer Career Ai Security Engineering AI Security Foundations AI Security Monitoring AI Security Tools AI Supply Chain AI System Inventory Architecture and Trust Boundaries Ats Systems Attack Career Development Corporate Culture Corporate Culture And Leadership Culture Security Cyber Security cybersecurity Cybersecurity Strategy Data Exposure and Privacy Defend Detection Engineering Distributed Governance Distributed Systems Economic Governance Education Evaluation and Regression Testing Evidence Evidence Based Governance Future of Work governance Governance And Resilience Governance Evidence and Customer Trust Governance, Risk & Compliance Hiring & Talent Hiring Strategy Incident Response Incident Response & Observability Leadership And Governance LLM Application Security Logging and Telemetry Map MLOps & Platform Security Model and Provider Risk Model Supply Chain Operational Risk Organizational Governance Organizational Resilience Platform Governance Privacy & Data Protection Prompt Injection Prompt Injection & Context Security Psychological Safety psychometrics RAG Authorization RAG Security Recruitment And Talent Red Teaming & Evaluations red-team seceng-workbench Secure Architecture & Design Secure RAG Security Architecture Stochastic Governance Stochastic Resilience Systemic Resilience Talent Acquisition Talent Engineering Team Engineering Technical Intelligence Threat Modeling Toolchain Integrity Training & Workshops Vendor Risk & Procurement Workforce Science Workplace Evolution

Map

The Future of AI Security Engineering: From AppSec to AgentSec to Autonomous SOCs

The future of AI Security Engineering is a platform discipline that extends AppSec into LLM applications, creates AgentSec for autonomous workflows, builds AI-native telemetry for detection and incident response, and turns governance into continuous evidence rather than annual paperwork.

9 min read

Defend

Security Monitoring for AI Agents: How to Detect Dangerous Tool Use Before Damage Happens

Security monitoring for AI agents requires tool-call telemetry, action-sequence detection, approval-state tracking, memory monitoring, credential visibility, anomaly detection, and kill-switch response paths. Dangerous tool use should be detected before it becomes data leakage, unauthorized change, financial impact, or customer-facing error.

10 min read

Defend

Least Privilege for AI Agents: Designing Permissions for Tools, APIs, Browsers, and Filesystems

AI agents need least privilege at the tool, API, browser, filesystem, credential, tenant, and action level. Safe design requires tool classification, read-only defaults, argument validation, scoped credentials, sandboxing, approval gates, and auditable enforcement outside the model.

13 min read

Defend

AI Incident Response: Playbooks for Prompt Injection, Model Abuse, Data Leakage, and Rogue Agents

Most incident teams already know how to isolate systems and preserve logs. AI changes the shape of the evidence. The response process must include prompts, retrieval context, tool actions, and model versions.

3 min read

Attack

Securing AI Agents: Identity, Memory, Tools, Permissions, and Kill Switches

Agent projects fail when teams treat autonomy as a product feature instead of a control problem. Once the agent can do work on behalf of a user, the attack surface moves from text to action.

3 min read

Attack

The Agentic Anarchy Problem: Why AI Agents Break Traditional IAM Models

AI agents break traditional IAM because they act across user intent, application authority, and tool permissions. A secure agent program requires explicit identity, delegated authorization, scoped credentials, and policy enforcement that lives outside the model.

12 min read