AI Security Research Portal
conceptactiveConcepts

Agent Security and Tool Abuse

Synthesis

Agentic systems expand the security boundary from model output to delegated actions, tool calls, memory, identity, and runtime authorization.

Evidence Base

This page was generated from the batch ingest of SRC-20260702-raw-papers-batch, SRC-20260702-raw-whitepapers-batch, and SRC-20260702-raw-news-batch. Treat it as a navigation and synthesis page; promote individual statements into claim pages when they become decision-relevant.

Representative Sources

TitleKindDateTagsRaw
Duo Brings Identity and Authorization Across AI Agent Gatewaysofficial_blog2026-06-17agent-identity, ai-gateway, authorization, mcp, non-human-identity, security-for-airaw
AI Agent Identity and Permission Challenges: How Uber and Auth0 Are Rethinking Access Controlnews2026-06-17agent-identity, delegated-authority, mcp, multi-agent, oauth, security-for-airaw
Securing the Agentic AI Frontier: Palo Alto Networks and Databricks Deliver a New Standard for AI Seofficial_blog2026-06-16agentic-ai, ai-gateway, data-security, governance, mcp, runtime-securityraw
An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenariospaper2026-06-15agent-security, ai-security, data-leakage, privacy, tool-using-agentraw
TrustedARI: Towards Trust-Native Agentic Routing Infrastructure for Agentic AIpaper2026-06-14agentic-ai, ai-security, multi-agent-systems, routing, trust-infrastructureraw
Prompt injection still drives most agentic AI security failures in productionnews2026-06-11agentic-ai, coding-agents, incidents, owasp, prompt-injection, security-for-airaw
Agents All the Way Down; A Methodology for Building Custom AI Agents from Substrate to Productionpaper2026-06-10agent-methodology, agentic-ai, ai-technology, audit-trail, custom-agents, security-boundariesraw
RAILS: Verification-Native Clearing For Agentic Commercepaper2026-06-07agent-integrity, agentic-commerce, ai-security, non-human-identity, settlement-risk, verificationraw
Careful Adoption of Agentic AI Servicesofficial_guidance2026-04-30ASD's ACSC, CISA, Canadian Centre for Cyber Security, NCSC-NZ, NCSC-UK, NSAraw
Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Ppaper2026-03-23Amin Milani Fard, Charoes Huang, Ngoc Phu Tran, Xin Huang, mcp-security, security-for-airaw
From Secure Agentic AI to Secure Agentic Web: Challenges, Threats, and Future Directionspaper2026-03agent-security, agentic-web, open-challenges, security-for-airaw
MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Serverspaper2025-08-19Guanquan Shi, Haifeng Sun, Haohua Du, Haoran Cheng, Suyuan Liu, Xiangyang Liraw

Open Questions

Related