When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills
arXiv:2608.03700v1 Announce Type: cross Abstract: Persona skills distill personal interaction histories into portable and executable artifacts for downstream agents. While enabling flexible personalization, this process concentrates fragmented personal signals, amplifies their impact through reuse, and challenges defenses designed for individual records or retrieval-based memory. To systematically investigate the safety of the persona-skill pipeline, we introduce AntiSkillBench, an end-to-end be
Record details
Published: 5 August 2026
Source: arXiv cs.CY
Category: Research
Topics: Privacy · Agents & autonomy · Finance, VC & PE
Retrieved: 5 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Behavioral Privacy Leakage in Agentic Negotiation: Formalizing and Mitigating Inference Attacks via Randomized Policies
HuggingFace Daily Papers · 6 July 2026
CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems
arXiv · 14 April 2026
Guideline-as-Oracle: Zero-Annotation Training of an Ophthalmic Telephone Triage Agent
arXiv cs.AI · 5 August 2026
ContextWeave: A Real-World Workflow Benchmark
arXiv · 5 August 2026
Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition
arXiv cs.AI · 5 August 2026
PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say
HuggingFace Daily Papers · 5 August 2026
How to cite this record
ethics.ai (5 August 2026), “When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills,” evidence record 16205, https://ethics.ai/record/16205 (originally published by arXiv cs.CY).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.