arXiv:2608. 14074v1 Announce Type: new Abstract: AI agents increasingly act on external systems through standardized tool-calling protocols such as the Model Context Protocol (MCP), yet no infrastructure layer constrains their actions to what a principal has verifiably authorized: authorization logic lives in application code, is neither signed nor independently auditable, and the resulting logs lack evidentiary value.
By Giovanni Racioppi
arXiv:2608. 06130v1 Announce Type: cross Abstract: AI agents performing cryptographic operations (signing Git commits, authenticating API calls, issuing certificates) currently store private keys in software-accessible locations: plaintext files, environment variables, or container memory.
By Leo Sambrook, Sampo Sovio
arXiv:2609.37196v1 Announce Type: cross
Abstract: Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allow...
By Yanjie Li, Xiangyu He, Xuelong Dai, Bin Xiao
arXiv:2608.30091v1 Announce Type: new
Abstract: Modern agent frameworks compose planners, tool agents, remote services, and shared specialists into runtime delegation graphs, but their revocation API...
By Lifei Liu, Haoran Yu, Xiaochong Jiang
arXiv:2605. 27488v2 Announce Type: replace-cross Abstract: Agentic systems increasingly run user-authored orchestration code that invokes tools, spawns subtasks, and delegates work across machines and clouds.
By Qiancheng Wu, Wenhui Zhang, Gan Fang, Sheng Mao, Biao Gao, David Levitsky, Shawna Murphy Butterworth, Rob Cameron
arXiv:2606. 11632v1 Announce Type: cross Abstract: Agentic infrastructure introduces a critical control-plane authorization problem: non-deterministic reasoning systems can propose high-stakes mutations to production resources, yet existing security mechanisms -- such as identity and access management (IAM), policy engines, consensus protocols, and audit logs -- either enforce static, context-unaware permissions or merely record actions post-execution.
By Jun He, Deying Yu
arXiv:2606. 22916v2 Announce Type: replace Abstract: AI agents increasingly act through external tools: they read private data, construct structured payloads, submit write requests, export records, and coordinate workflows across application boundaries.
By Genliang Zhu, Chu Wang
arXiv:2606. 04193v1 Announce Type: cross Abstract: Current AI agent observability is structurally compromised: the entity producing the activity log is the same entity whose activity is being logged.
By Juan Figuera
The paper examines the security challenges of delegating authority to autonomous LLM agents that act on users’ behalf. It introduces a threat model with four adversaries and eight security requirements, demonstrates that current frameworks (LangGraph, CrewAI, AutoGen, MCP) fail to meet these standards, and presents an authorization broker that blocks all identified threats with minimal overhead. The broker is shown to resist numerous attacks and limits compromised sub‑agents to their delegated tasks, and its principles are implemented in VotalAI’s LLM Shield.
By Panduranga Sai Varma Dantuluri, Jyotirmoy Sundi
The paper introduces PACE (Policy‑Attested Contract Execution), a framework that sits between large‑language‑model (LLM) based autonomous AI agents and on‑chain DeFi operations. PACE defines typed transaction intents, a deterministic policy verifier, and signed Policy Decision Records (PDRs) that cryptographically bind an approved intent, policy, and simulation report to the exact on‑chain execution bytes, providing replay and expiration protection. In evaluations across 40 tasks and six baselines, PACE achieves zero unsafe executions and zero false positives, outperforming unguarded agents by a large margin.
By Rabimba Karanjai (Larry), Yang Lu (Larry), Richard Williamson (Larry), Hemanth Hm (Larry), Prakhar Mehrotra (Larry), Lei Xu (Larry), Weidong (Larry), Shi
The paper presents a systematic security analysis of Google’s Agent Payments Protocol (AP2) version 2.0, focusing on its roles, transaction lifecycle, and deployment architectures. It identifies 48 threats across five attack families, scores them with the AIVSS, and demonstrates eight high‑risk threats with proof‑of‑concept attacks and mitigations. The study also introduces a deployment‑aware scanner to map threats to various checks, showing that signed mandates alone cannot guarantee user intent when pre‑authorization context is manipulated.
By Avital Aviv, Parth A. Gandh, Ron Bitton, Asaf Shabtai
arXiv:2609.22944v1 Announce Type: cross
Abstract: Autonomous AI agents increasingly act across organizational boundaries on behalf of human operators: they invoke third-party services, delegate subta...
By Oliver Aleksander Larsen, Mahyar Tourchi Moghaddam