APEX: Active Protection at Execution Boundaries for LLM Agents
cs.CR, cs.AI
Submitted: 2026-10-03
Updated: 2026-10-07
Code: https://github.com/ZhengXR930/APEX_official
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Influence Is Not Authority: When Causal Guardrail Signals Make Legitimate Tool Use Look Like an Attack in Tool-Using LLM Agents
- Combining Pre- and Post-Demosaicking Noise Removal for RAW Video
- Securing AI Agents with Information-Flow Control
- Defeating Prompt Injections by Design
- The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck
- Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents
- Defending Against Indirect Prompt Injection Attacks With Spotlighting
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Taxonomy, Evaluation and Exploitation of IPI-Centric LLM Agent Defense Frameworks
- Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework
- SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
- SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
- SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
- Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
- HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense
- STAC: When Innocent Tools Form Dangerous Chains for LLM Agents
- AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
- MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP
- PhantomSkill: Malicious Code Injection in Agent Skill Ecosystems
- IterInject: Indirect Prompt Injection Against LLM Agents via Feedback-Guided Iterative Optimization
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs