Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection

Summary

Researchers tested whether self-evolving personal agents, which learn from user feedback, become less robust to indirect prompt injection, where hidden instructions in third-party content hijack the agent. In a two-phase setup on a real personal agent, the average attack success rate rose by 14.0 to 48.8 percentage points under skill evolution and by 3.0 to 39.3 percentage points under reinforcement learning, compared with a base agent that does not evolve.

Topics

• Prompt injection and jailbreaks

Related items

• InfoUnderstanding and Mitigating Role Spoofing in LLMsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• HighCVE-2026-119050: Agno PandasTools unsafe reflection allows code execution via prompt injectionSimilar attack · NVD/CVE Database
• Low3 Ways AI Agents Already Operate in Your BrowserSimilar attack · BleepingComputer
• InfoAdversa AI Launches Coding Agent Security Platform to Block Cyberattacks on AI Agents in Real TimeSimilar attack · Adversa AI Blog
• InfoSEAL: Sealed Queries for Local Sanitization against Indirect Prompt InjectionSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)