# Governing Execution Risk in Agentic AI Systems: A Trajectory-Guided Framework for Red Teaming

arXiv: https://arxiv.org/abs/2608.04018 · HTML: https://mlsanity.com/paper/2608.04018/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)
- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 22 of 22)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks](https://mlsanity.com/paper/2412.14161/) (2024)
- [Defending Against Indirect Prompt Injection Attacks With Spotlighting](https://mlsanity.com/paper/2403.14720/) (2024)
- [SecAlign: Defending Against Prompt Injection with Preference Optimization](https://mlsanity.com/paper/2410.05451/) (2024)
- [WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks](https://mlsanity.com/paper/2504.18575/) (2025)
- [MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents](https://mlsanity.com/paper/2502.05174/) (2025)
- [AdvAgent: Controllable Blackbox Red-teaming on Web Agents](https://mlsanity.com/paper/2410.17401/) (2024)
- [Can Indirect Prompt Injection Attacks Be Detected and Removed?](https://mlsanity.com/paper/2502.16580/) (2025)
- [RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection](https://mlsanity.com/paper/2510.04885/) (2025)
- [EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System](https://mlsanity.com/paper/2509.10540/) (2025)
- [T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search](https://mlsanity.com/paper/2603.22341/) (2026)

## Abstract (arXiv)

AI agents are increasingly embedded in organizational workflows, where they interact with external information sources and invoke digital tools to perform operational tasks. As organizations adopt such systems, a critical challenge is identifying and mitigating risks arising from malicious or untrusted external information that can steer agents toward unintended actions. Existing red-teaming approaches largely rely on fixed attack templates or final attack outcomes, providing limited visibility into how attacks unfold through multi-step reasoning and tool use. We argue that agent execution risk should be understood as a trajectory-level phenomenon. Building on this perspective, we propose TrajRed, a trajectory-guided red-teaming framework that uses execution trajectories to uncover vulnerabilities in agentic AI systems. We further develop TrajGuard, a runtime governance layer that uses high-risk trajectories discovered during red teaming to monitor and intervene in ongoing workflows. Experiments on AgentDojo across four organizational task suites show that TrajRed identifies substantially stronger vulnerabilities than fixed-template and automatic red-team baselines. Building on these vulnerability findings, TrajGuard reduces attack success across all evaluated attack methods to near zero while preserving benign task utility. Together, the results demonstrate that execution trajectories provide a practical foundation for both red teaming and risk control in agentic AI systems. This work highlights the importance of governing agent execution in organizational AI deployments.