Who Is Your Agent Serving? Provider-Side Indirect Prompt Injection in Proactive Agents

cs.CR, cs.AI

Submitted: 2026-10-04

Updated: 2026-10-04

Comments: 30 pages, 7 figures, 13 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents
• Do Proactive Agents Need an LLM to Decide When to Act?
• Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants
• Detecting Malicious AI Agents Through Simulated Interactions
• Commercial Persuasion in AI-Mediated Conversations
• PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory

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