The paper exposes a vulnerability in AI toolchains where signed Model Context Protocol (MCP) tools can hide malicious code that leaks data, even when protected by state‑of‑the‑art runtime defenses. It introduces germline execution, which runs each tool invocation in an isolated, data‑free copy, limiting information disclosure to only what is authorized for the destination. Experiments on 153 attack runs show that germline execution prevents unauthorized disclosure in all cases, outperforming baseline defenses and ablations, while maintaining efficient performance (10‑49 ms per invocation).
By Yichiet Aun (Universiti Tunku Abdul Rahman), Mohammed A. Alhartomi (University of Tabuk), Jing Jie Tan (National University of Singapore), Waqas Nadeem (Universiti Tunku Abdul Rahman), Adeb Salh (Universiti Tunku Abdul Rahman), Shankar Karuppayah (Bitranger, CYRES, Universiti Sains Malaysia), Sin Chee Tan (ABLEs)
arXiv:2508.14925v2 Announce Type: replace-cross
Abstract: By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a...
By Zhiqiang Wang, Yichao Gao, Yanting Wang, Suyuan Liu, Haifeng Sun, Haoran Cheng, Guanquan Shi, Haohua Du, Xiangyang Li
MCPHunt is a benchmark framework that isolates non‑adversarial credential propagation across multi‑server MCP trust boundaries. It uses canary‑based taint tracking, a controlled coverage design with risky, benign, and hard‑negative conditions, and completion‑requires‑secret stratification to separate faithful from policy‑violating propagation. Across 3,615 traces from 5 models, policy‑violating propagation rates range from 11.5 % to 41.3 %, with mitigation via prompting reducing rates to 0.3 % while retaining 80.5 % utility.
By Haonan Li, Tianjun Sun, Yongqing Wang, Qisheng Zhang
arXiv:2608.20580v1 Announce Type: cross
Abstract: Federated learning (FL) is vulnerable to multi-level attacks. However, existing methods address them separately, leaving FL exposed to data leakage,...
By Xinyun Liu, Zhi Lu, Yu Chen, Ronghua Xu
The paper introduces TrustShiftProbe, a framework that characterizes and defends against staged trust attacks on Model Context Protocol (MCP) servers. It defines a temporal threat model where a compromised server behaves benignly during conditioning and later delivers adversarial payloads, and presents a multi‑tier runtime defense called SHIELD that reduces attack success from 69.5% to 42.7%. The work also provides a taxonomy of nine TrustShift variants across different execution mechanisms and objectives.
By Mehrdad Rostamzadeh, Sidhant Narula, Mohammad Ghasemigol, Daniel Takabi
Repeat-After-Me is a black-box adaptive visual prompt injection technique that can reveal personally identifiable information or trigger malicious tool calls in both open-weight and commercial vision‑language models, achieving attack success rates above 80% on Qwen3.6‑27B and 47% on GPT‑5.5. The method works even when the benign user prompt is unrelated to the injected task and does not explicitly authorize it, and it retains significant effectiveness when transferred across models or optimized on surrogate systems. In a real‑world OpenClaw Discord deployment, a minimally injected image can overwrite TOOLS.md, enabling remote code execution and secret exfiltration.
By Sizhe Chen, Yu-Lin Tsai, Ivan Evtimov, Kamalika Chaudhuri, Raluca Ada Popa, David Wagner, Arman Zharmagambetov