Evaluating Authorization and Trust Boundaries in Agentic Orchestration Frameworks

Agentic AI systems extend large language models with tools, memory, and multi-agent collaboration, introducing security risks at orchestration boundaries. These risks depend on how identities are represented, operations are authorized, and instructions or information propagate between components. We evaluate LangChain, LangGraph, AutoGen, and OpenClaw through twelve experiments mapped to the OWASP Top 10 for Agentic Applications using a common LLM (gpt-4o-mini). The experiments cover prompt injection, unauthorized resource access and command execution, memory poisoning, and inter-agent trust and identity attacks. Adversarial inputs induced unauthorized tool invocation, while tool chaining, stale filesystem validation, encoded instructions, and inter-agent delegation exposed weaknesses in authorization across component boundaries. Memory poisoning showed that untrusted state can influence responses, a risk distinct from conventional access-control violations. In the evaluated protected configurations, explicit authorization, controlled capability assignment, filesystem containment, and execution safeguards prevented specific unauthorized operations. The findings emphasize preserving authorization and information-trust boundaries throughout agentic workflows rather than treating framework capabilities or model-level instructions as sufficient security guarantees.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.21259
Primary Topic
Adversarial Robustness in Machine Learning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Evaluating Authorization and Trust Boundaries in Agentic Orchestration Frameworks

Kshitiz Aryal, Maanak Gupta, Elisa Bertino, Sahaya Jestus Lazer
arXiv (Cornell University)
Adversarial Robustness in Machine Learning
preprint

Evaluating Authorization and Trust Boundaries in Agentic Orchestration Frameworks

Kshitiz Aryal, Maanak Gupta, Elisa Bertino, Sahaya Jestus Lazer
preprint en

Abstract

Agentic AI systems extend large language models with tools, memory, and multi-agent collaboration, introducing security risks at orchestration boundaries. These risks depend on how identities are represented, operations are authorized, and instructions or information propagate between components. We evaluate LangChain, LangGraph, AutoGen, and OpenClaw through twelve experiments mapped to the OWASP Top 10 for Agentic Applications using a common LLM (gpt-4o-mini). The experiments cover prompt injection, unauthorized resource access and command execution, memory poisoning, and inter-agent trust and identity attacks. Adversarial inputs induced unauthorized tool invocation, while tool chaining, stale filesystem validation, encoded instructions, and inter-agent delegation exposed weaknesses in authorization across component boundaries. Memory poisoning showed that untrusted state can influence responses, a risk distinct from conventional access-control violations. In the evaluated protected configurations, explicit authorization, controlled capability assignment, filesystem containment, and execution safeguards prevented specific unauthorized operations. The findings emphasize preserving authorization and information-trust boundaries throughout agentic workflows rather than treating framework capabilities or model-level instructions as sufficient security guarantees.

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