Hyun Sim ↗
RESEARCH · 2026 · SSRN 7639338

From Compromise to Consequence:
Capability-Weighted Cascade Risk in Agentic AI Systems.

Hyun Sim · Calvin University

01 / SUMMARY

Measure consequences, not only compromises.

This paper proposes a consequence-oriented measurement layer for agentic AI security. Instead of counting only how many components are compromised, it weights the effective capability, autonomy, and asset impact that an attacker can reach through trust and delegation paths.

C/01

CWCE

Capability-Weighted Cascade Exposure weights the probability of influence over each component by effective capability, action autonomy, and asset impact.

C/02

PCE

Persistent Capability Exposure extends the consequence model across time so long-lived memory, delegation, and trust effects are represented.

C/03

PTC

Privilege-Trust Coupling measures how strongly trust relationships point toward more privileged components before an attack occurs.

C/04

Architecture

The work evaluates role scoping, provenance, independent execution gates, least privilege, memory quarantine, and zero-trust boundaries using synthetic stochastic simulation.

02 / RESULTS

Consequence-weighted exposure changed more than raw prevalence.

Across 180,000 non-operational Monte Carlo trials, architectures with stronger authorization, provenance, and isolation reduced consequence-weighted exposure substantially relative to a shared-trust baseline.

ROLE SCOPING

59.3% lower mean CWCE

Relative to the shared-trust baseline in the reported synthetic model.

MODEL
PROVENANCE + GATE

88.6% lower mean CWCE

Independent execution authorization further reduced consequence-weighted exposure.

MODEL
ZERO TRUST + QUARANTINE

97.3% lower mean CWCE

The most restrictive synthetic design combined memory quarantine and zero-trust controls.

MODEL
03 / RESEARCH RECORD

Publication metadata.

The authoritative publication record is maintained by SSRN. This first-party page provides a stable author and topic index for search engines.

AUTHOR

Hyun Sim

Cybersecurity and AI security researcher; professional name Kenneth Sim.

Profile ↗
IDENTIFIER

DOI 10.2139/ssrn.7639338

SSRN abstract 7639338 · posted 21 October 2026.

Resolve ↗
KEYWORDS

Agentic AI · LLM agents · AI security

Memory poisoning, prompt injection, multi-agent systems, zero trust, capability-weighted risk, authorization, and secure autonomy.

RESEARCH