Evaluating Authorization and Trust Boundaries in Agentic Orchestration Frameworks
Organizations: Tennessee Tech University, Cookeville, United States · University of Nebraska Omaha, Omaha, United States · Purdue University, West Lafayette, United States
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.
Figures & tables
| Dimension | LangChain | LangGraph | AutoGen | OpenClaw |
|---|---|---|---|---|
| State/persistence | Agent/message state; configurable persistence | Graph state; checkpoints | Agent/team state; save/load | Persistent workspaces/sessions |
| Communication | Model–tool loop | Graph state/message flow | Runtime agent messaging | Gateway agent/session routing |
| Identity representation | App-defined agent/tool roles | Nodes/agents; thread IDs | Explicit agent IDs | Agent/session IDs |
| Authorization | App/middleware tool access and approval | Graph routing, tool access, interrupts | Per-agent tools and approvals | Layered tool policies; per-agent restrictions |
| Trust propagation | Tool requests; app-defined checks | State transfer; routing checks | Agent handoffs; supervisory checks | Session routing; runtime policy checks |
| Execution/recovery | Runtime-dependent; no mandatory sandbox | Runtime-dependent; checkpoint recovery | Local/container execution; state restoration | Configurable sandbox; persistent sessions |
| Exp. | Objective | Layer | Attack Surface | Primary Asset | T-Code | ASI |
|---|---|---|---|---|---|---|
| E1 | Direct prompt injection | Model | User instruction manipulation | Task integrity | T6 | ASI01 |
| E2 | Indirect prompt injection | Model / context | Untrusted external content | Task integrity | T6 | ASI01 |
| E3 | Unauthorized tool chaining | Orchestration / tool | Tool composition and invocation | Tool authorization | T2 | ASI02 |
| E4 | Unauthorized shell execution | Execution | Shell-command interface | Execution control | T11 | ASI02, ASI05 |
| E5 | Encoded payload execution | Execution | Payload decoding and execution | Execution control | T11 | ASI05 |
| E6 | Symlink escape (TOCTOU) | Filesystem | Symlink and path resolution | Filesystem boundary | T2 | ASI02 |
| Var. | Attack | LC | LG | AG | OC |
|---|---|---|---|---|---|
| A | Basic override | S | S | S | S |
| B | HOUYI separator | S | S | S | S |
| C | Authority claim | S | S | S | S |
| D | Delegation/audit | U/– | U/– | S | U/– |
| Exp. | Attack Goal | LC | LG | AG | OC |
|---|---|---|---|---|---|
| E3 | Tool chaining | V | V | V | V |
| E6 | Symlink (TOCTOU) | V | V | V | V |
| E7 | Path traversal | S | S | S | S |
| Exp. | Attack Goal | LC | LG | AG | OC |
|---|---|---|---|---|---|
| E4 | Shell execution | A/I | R | R | R |
| E5 | Encoded payload | P | Y | Y | Y |
| E8 | Delegated command | B | B | B | B |
| Framework | E9 ASR | E9 Clean Acc. | E10 ASR | E10 Clean Acc. | E10 FPR |
|---|---|---|---|---|---|
| LangChain | |||||
| LangGraph | |||||
| AutoGen | |||||
| OpenClaw |
| E11 | Deleg. | Auth. | Secret | Outcome |
|---|---|---|---|---|
| B1 | Forwarded | Not checked | Disclosed | Compromised |
| B2 | Forwarded | Rejected | Not disclosed | Protected |
| E12 | Identity | Auth. | Marker | Outcome |
| A | Accepted | Approved | Created | Compromised |
| B | Rejected | Rejected | Not created | Protected |
AI Agent Security
Artificial intelligence agent security studies attacks and safeguards for tool-using, persistent, and collaborative systems across digital and physical settings.
See all 558 papers