# Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents

arXiv: https://arxiv.org/abs/2506.10171 · HTML: https://mlsanity.com/paper/2506.10171/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 1 of its 29 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)
- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 1 of 1)

- [AirGapAgent: Protecting Privacy-Conscious Conversational Agents](https://mlsanity.com/paper/2405.05175/) (2024)

## Built on by (most cited first, 7 of 7)

- [Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation](https://mlsanity.com/paper/2512.16310/) (2025)
- [AudAgent: Automated Auditing of Privacy Policy Compliance in AI Agents](https://mlsanity.com/paper/2511.07441/) (2025)
- [NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agents](https://mlsanity.com/paper/2601.14660/) (2026)
- [ToolMinimize: Auditing and Rewriting LLM Agent Tool Calls to Minimize Privacy Exposure](https://mlsanity.com/paper/2608.24957/) (2026)
- [Say Something Else: Rethinking Contextual Privacy as Information Sufficiency](https://mlsanity.com/paper/2604.06409/) (2026)
- [Inferring Hidden User Models from the Behavior of Personalized LLM Agents](https://mlsanity.com/paper/2609.03815/) (2026)
- [SEABench: Benchmarking Endogenous Misalignment In Self-Evolving Agents](https://mlsanity.com/paper/2609.35596/) (2026)

## Abstract (arXiv)

LLM agents have begun to appear as personal assistants, customer service bots, and clinical aides. While these applications deliver substantial operational benefits, they also require continuous access to sensitive data, which increases the likelihood of unauthorized disclosures. Moreover, these disclosures go beyond mere explicit disclosure, leaving open avenues for gradual manipulation or sidechannel information leakage. This study proposes an auditing framework for conversational privacy that quantifies an agent's susceptibility to these risks. The proposed Conversational Manipulation for Privacy Leakage (CMPL) framework is designed to stress-test agents that enforce strict privacy directives against an iterative probing strategy. Rather than focusing solely on a single disclosure event or purely explicit leakage, CMPL simulates realistic multi-turn interactions to systematically uncover latent vulnerabilities. Our evaluation on diverse domains, data modalities, and safety configurations demonstrates the auditing framework's ability to reveal privacy risks that are not deterred by existing single-turn defenses, along with an in-depth longitudinal study of the temporal dynamics of leakage, strategies adopted by adaptive adversaries, and the evolution of adversarial beliefs about sensitive targets. In addition to introducing CMPL as a diagnostic tool, the paper delivers (1) an auditing procedure grounded in quantifiable risk metrics and (2) an open benchmark for evaluation of conversational privacy across agent implementations.