ToolHijacker: Prompt Injection Attack to Tool Selection in LLM Agents
Apr 2025 paper introducing a no-box attack that injects a malicious tool document into an agent's tool library to consistently hijack tool selection. Finds that StruQ, SecAlign, DataSentinel, and perplexity detection are all insufficient defenses.
- from
- Prompt Injection
- added
- 2026-10-10
- likes
- 0
similar
-
prompt-shield github.com
Self-learning prompt injection detection engine with novel cross-domain techniques: Smith-Waterman sequence alignment (bioinformatics), stylometric discontinuity detection (forensic linguistics), and adversarial fatigue tracking (materials science). 27 detectors, 6 output…
-
The Landscape of Prompt Injection Threats in LLM Agents (SoK) arxiv.org
Feb 2026 systematization-of-knowledge paper with a unified taxonomy covering attack payload strategies (heuristic vs. optimisation-based) and defense intervention stages (text, model, execution). Introduces the AgentPI benchmark for context-dependent agent tasks that all prior…
-
MCP Prompt Injection: How AI Gets Hacked youtube.com
Nov 2025 hands-on walkthrough showing how prompt injection exploits tool metadata and trust boundaries in Model Context Protocol-integrated agents, which remain a primary attack surface as MCP adoption widens.
-
Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection arxiv.org
This paper explores the concept of Indirect Prompt Injection attacks on Large Language Models (LLMs) through their integration with various applications. It identifies significant security risks, including remote data theft and ecosystem contamination, present in both…
-
Prompt Injection 2.0: Hybrid AI Threats arxiv.org
Jul 2025 paper showing how prompt injections now combine with XSS, CSRF, AI worm propagation, and multi-agent infections to evade traditional WAFs entirely. Evaluates Preamble's classifier, data-tagging, and RL-based defenses against these hybrid scenarios.
-
Indirect Prompt Injection Attacks: Hidden AI Risks crowdstrike.com
CrowdStrike's Dec 2025 analysis of IPI TTPs targeting enterprise GenAI, including attacker-controlled document poisoning, RAG context manipulation, and practical detection signals for SOC workflows.
Prompt Injection › Research Papers: “Apr 2025 paper introducing a no-box attack that injects a malicious tool document into an agent's tool library to consistently hijack tool selection. Finds that StruQ, SecAlign, DataSentinel, and perplexity detection are all insufficient defenses.”