ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation

📅 2026-05-26
📈 Citations: 0
Influential: 0
📄 PDF

career value

179K/year
🤖 AI Summary
This work addresses the "privilege laundering" problem in tool-augmented agents, where individually benign tool permissions can combine to enable unsafe behaviors. The authors propose a transparent runtime defense mechanism that requires no modifications to either the agent or tool servers. Built upon an MCP proxy, the approach introduces receiver-oriented capability budgets and enforces monotonic capability decay through intersection-based propagation, ensuring that combined permissions can only weaken—not strengthen—during composition. By integrating explicit information flow control with a trusted allowlist, the method reduces attack success rates from 25–68% to 0–4.8% across 82 tasks while maintaining normal task completion rates of 96–100%, substantially outperforming existing baselines.
📝 Abstract
Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterprise services at runtime. This creates a safety gap in tool composition: an agent can satisfy every per-tool permission check and still produce an unsafe end-to-end effect, such as reading a confidential document, summarizing it, and sending the summary to an external endpoint. We call this failure mode permission laundering. ChainCaps addresses it with a runtime rule: every value carries a sink-specific capability budget, and tool composition propagates budgets by intersection. A value can preserve or lose authority as it moves through a tool chain, but it cannot gain new authority through composition. We implement ChainCaps as a transparent MCP proxy that requires no changes to the agent or tool servers. On 82 tasks across five frontier models from three providers, ChainCaps reduces attack success rate from 25-68% to 0-4.8% while preserving 96-100% benign completion. In replay experiments, it also outperforms scalar-IFC and per-function-isolation baselines. Manifest quality is the dominant deployment bottleneck: expert manifests reach 100% attack blocking, while naive manifests fall to 27.3%. Our claims are limited to explicit-flow composition safety under trusted manifests and proxy-visible data movement, a practical gap in deployed tool-using agents today.
Problem

Research questions and friction points this paper is trying to address.

tool-using agents
permission laundering
composition safety
capability attenuation
runtime security
Innovation

Methods, ideas, or system contributions that make the work stand out.

ChainCaps
permission laundering
capability attenuation
tool composition safety
information flow control
🔎 Similar Papers
2024-03-04Proceedings of the 17th International Conference on Agents and Artificial IntelligenceCitations: 3
X
Xiaochong Jiang
Independent Researcher, Seattle, WA, USA
S
Shiqi Yang
Independent Researcher, New York City, NY, USA
Z
Ziwei Li
King Abdullah University of Science and Technology, Saudi Arabia
L
Lifei Liu
Independent Researcher, Seattle, WA, USA
H
Haoran Yu
Independent Researcher, Seattle, WA, USA
Y
Yichen Liu
Independent Researcher, Seattle, WA, USA