Skill-equipped agents reproduce target users' attributes and language, enabling impersonation across unseen contexts¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? Agents equipped with distilled persona skills reveal target-user attributes under direct queries (Field QA accuracy) and reproduce target-user language in persona-relevant scenarios (VocabGain). → Yongli Xiang 2026
Evidence¶
Yongli Xiang 2026¶
Yongli Xiang, Zhifang Zhang, Bojun Yang, Ziming Hong, Lei Feng, Miao Xu, Tongliang Liu. (2026). When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills. arXiv. https://arxiv.org/abs/2608.03700 doi:10.48550/arxiv.2608.03700
q2 · i? · design · r2
Agent-level impersonation evaluation in Table 1, with skill-equipped agents answering field questions and generating persona-relevant text judged against ground-truth profiles. Gemini 3.6 Flash reaches "up to 48.4 QA Acc and 40.0 VocabGain overall", and Claude Haiku 4.5 reaches "up to 52.5 QA Acc and 19.9 VocabGain overall". Descriptive percentages; no effect sizes printed.
"GPT 5.4 with three-stage Distill reaches 56.0 overall QA Acc, recovering demographics (32.6), background (49.1), personality (48.1), and especially communication traits (75.9). Its VocabGain is also positive across all four dimensions (22.3, 37.1, 17.6, 87.7), showing that generated queries move closer to target-user outputs."
Discussion¶
Related Claims¶
- Active defenses (Privacy Sanitization, Adversarial Obfuscation) reduce but do not eliminate persona-skill leakage, leaving personality and background exposed — related
- Persona-skill distillation encodes substantial private information into skill artifacts, persisting across agent backbones and distillation protocols — a broader claim this one bears on
- Skill-level leakage is strongest for communication style and personality, not explicit demographics — related
- Passive backdoor defense (SBD) effectiveness is distillation-dependent, degrading under persona-centric abstraction — related
- Privacy protection in the framework is partial: three residual leakage channels remain open — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
agent-level-impersonation-qa-acc-vocabgain |
title |
Skill-equipped agents reproduce target users' attributes and language, enabling impersonation across unseen contexts |
description |
Skill-equipped agents reproduce target users' attributes and language, enabling impersonation across unseen contexts |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — yongli-xiang-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.