Answers are grounded in this paper and cite their sources.
Computational evaluation reveals severe architectural intent collapse across 25 LLM agent frameworks, indicating that context flattening prevents models from distinguishing descriptions from commands.
Tool-level attacks on Large Language Model (LLM) agents—poisoned tool descriptions, prompt injection, and capability misrepresentation—are universally effective, yet no existing defense provides comprehensive protection. We propose Architectural Intent Collapse (AIC), a formal framework capturing the systematic loss of communicative intent when text from heterogeneous sources is flattened into a single context window. Grounded as a novel instantiation of the Confused Deputy Problem, AIC reveals that the missing boundary is not permission but intent: the architecture cannot distinguish descriptive statements from prescriptive commands. We formalize AIC via an architectural collapse operator, introduce Intent Separation Degree (ISD) as a measurable metric, and develop a mechanism-based taxonomy of five intent-disguise attack types, including two previously undescribed (Conditional Latency and Inference Inducement). Experiments across 25 framework–model combinations (employing GPT-4o, Claude-4-Sonnet, Gemini-2.5-Pro, DeepSeek-V3, and Qwen3-32B as LLM backends) confirm that ISD degrades with description verbosity, strongly predicts defense effectiveness (r=−0.97), and is uniformly low across all current frameworks. Three root-cause defense principles are derived; one retains substantial protection against adaptive attackers. This research is useful for agent framework designers, security practitioners, and researchers seeking a principled understanding of why tool-level attacks succeed and how architectural defenses can address their root cause.
No takes yet. Share an insight, caveat, or question.
Feng et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: