arXiv AI
AgenTRIM: Tool Risk Mitigation for Agentic AI
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 3
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents
arXiv:2607. 29254v1 Announce Type: new Abstract: AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential real-world actions.
arXiv AI
Sep 28
AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents
AgentXploit is a two‑role auditing system that separates repository‑level attack‑path discovery from runtime exploitation for AI agents. The Analyzer Agent traces attacker‑controlled inputs to sensitive operations and records candidate attack paths, while the Exploiter Agent turns these paths into concrete attacks and refines them using runtime feedback. The system is evaluated on AgentXploit‑Bench, a benchmark of 72 reproducible vulnerabilities across 12 open‑source AI‑agent systems, achieving 59.3% end‑to‑end success compared to 38.4% for Codex, and 79.2% attack success on AgentDojo versus 52.7% for AgentVigil.
arXiv AI
Jul 22
Data Leakage Prevention in Agentic Applications via Preemptive Hardening
arXiv:2607. 18847v1 Announce Type: cross Abstract: Agentic systems integrate LLM driven planning with interfaces to external tools, making data leakage and tool misuse feasible via instruction/data boundary failures and prompt injection attacks.
arXiv AI
4d ago
MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems
MAS-Guard is a unified framework designed to safeguard both single- and multi-agent large language model (LLM) systems. It introduces a local Agent Guardrail (A-Guard) layer that uses task-specific experts to evaluate agentic events, and a system-level Control Plane that applies deterministic structural checks and semantic assessments to routes, capabilities, and message content. The framework enforces interventions—allow, reflection, confirmation, and block—across benchmarks, reducing attack success rates by 71.5‑86.3% while maintaining utility on benign tasks.
arXiv AI
Jun 2
SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents
arXiv:2606. 02302v1 Announce Type: cross Abstract: Autonomous LLM agents increasingly operate in stateful environments where they access tools, files, memory, and external services.
arXiv AI
Aug 11
Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control
arXiv:2605. 18414v2 Announce Type: replace-cross Abstract: Large language models increasingly operate as autonomous agents that select and invoke tools from large registries.