Paper

When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents

Unreadunread

AI summary

arXiv:2605. 24069v1 Announce Type: new Abstract: The rise of tool-using Large Language Model (LLM) agents, standardized by protocols like the Model Context Protocol (MCP), has unlocked unprecedented autonomous execution capabilities for LLM Agents by integrating external open-domain knowledge and tools.

Reading status

Priority

About this paper

Authors: Shi Liu, Xuehai Tang, Xikang Yang, Liang Lin, Biyu Zhou, Wenjie Xiao, Wantao Liu
Released: 2026-05-26 (2mo ago)
Topic: Related to current project
Relation to my work: Read next because When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, text, rect, correct, eval, rate, test, language. Source: arxiv cs.CR (Cryptography and Security).
arXiv: 2605.24069

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.