Weighing the Envelope: Component Weight and Arbitration in Envelope-Layer Defenses for a Single LLM Agent

The envelope layer is the channel through which malicious content enters an LLM agent. Prior work established label and memory effects on multi-agent A2A envelopes, but the weight structure when MCP tools and memory coexist in a single agent remains unclear. Our threat model assumes an attacker pre-plants a malicious tool and poisons long-term memory; a benign user request inadvertently triggers it, and the attacker never enters the conversation. Following GDA Measurement and A/B/C/D, we measure how labels, memory, tool roles, and the backend shape invocation decisions across label-memory conflict, tool roles, robustness, and tool generalization. A tool-side forced-verification label substantially reduces semantic breach, but strong success memory pulls it back; a memory-side downgrade statement returns the outcome to the level of the label alone. The label works through mandatory implementation inspection plus default denial, not length or format; memory authorization wording erodes it with dose, while position and multi-turn pressure do not change the defense direction. Tool roles divide label effects into substitution, suppression, and boundary failure: low penetration is not safety, local leakage is the main residual risk, and a second malicious tool shows the same direction. Envelope labels are not a switch but a measurable, reversible weight constrained by backend and tool role, acting as a soft gate and risk signal within a broader defense rather than a substitute for permissions, sandboxing, or human review.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-18
DOI
https://doi.org/10.48550/arxiv.2611.23844
Primary Topic
Adversarial Robustness in Machine Learning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Weighing the Envelope: Component Weight and Arbitration in Envelope-Layer Defenses for a Single LLM Agent

Yuelin Han
arXiv (Cornell University)
Adversarial Robustness in Machine Learning
preprint

Weighing the Envelope: Component Weight and Arbitration in Envelope-Layer Defenses for a Single LLM Agent

Yuelin Han
preprint en

Abstract

The envelope layer is the channel through which malicious content enters an LLM agent. Prior work established label and memory effects on multi-agent A2A envelopes, but the weight structure when MCP tools and memory coexist in a single agent remains unclear. Our threat model assumes an attacker pre-plants a malicious tool and poisons long-term memory; a benign user request inadvertently triggers it, and the attacker never enters the conversation. Following GDA Measurement and A/B/C/D, we measure how labels, memory, tool roles, and the backend shape invocation decisions across label-memory conflict, tool roles, robustness, and tool generalization. A tool-side forced-verification label substantially reduces semantic breach, but strong success memory pulls it back; a memory-side downgrade statement returns the outcome to the level of the label alone. The label works through mandatory implementation inspection plus default denial, not length or format; memory authorization wording erodes it with dose, while position and multi-turn pressure do not change the defense direction. Tool roles divide label effects into substitution, suppression, and boundary failure: low penetration is not safety, local leakage is the main residual risk, and a second malicious tool shows the same direction. Envelope labels are not a switch but a measurable, reversible weight constrained by backend and tool role, acting as a soft gate and risk signal within a broader defense rather than a substitute for permissions, sandboxing, or human review.

arXiv (Cornell University)
Adversarial Robustness in Machine Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon