arXiv AI
HASTE: Evolving Agent Harnesses Against Emerging Attacks Using Sparse Evidence
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 14
Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents
arXiv:2608. 12977v1 Announce Type: cross Abstract: The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats.
arXiv Computation and Language
Oct 1
HARDE: Optimizing Agent Harnesses for Runtime Risk Detection and Execution Control
arXiv:2609.38291v1 Announce Type: cross Abstract: Large language model (LLM) agents are vulnerable to safety risks such as injected malicious instructions or misleading information, motivating runtim...
arXiv AI
Jun 19
The Autonomy Tax: Defense Training Breaks LLM Agents
arXiv:2603. 19423v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks.
arXiv AI
Aug 19
HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety
HarnessRisk is a lifecycle-oriented benchmark for evaluating safety in agent harnesses that manage tools, extensions, state, permissions, and external actions. It defines six operational phases—Harness Configuration, Capability Extension, Runtime Operation, State Persistence, Action Control, and Incident Recovery—and includes 128 sandboxed cases pairing benign user objectives with adversarial instructions. Across three harnesses, six language models, and 14 configurations, attack success rates vary from 12.6% to 80.9%, with the most vulnerable phase being Harness Configuration. "whyItMatters":"The benchmark demonstrates that safety failures can arise in multiple harness responsibilities and that even explicit risk detection does not guarantee safe action, underscoring the need for comprehensive evaluation across model and harness configurations."
arXiv AI
Sep 1
T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search
The paper introduces T-MAP, a trajectory‑aware evolutionary search technique designed to red‑team large language model agents by exploiting vulnerabilities that arise during multi‑step tool execution. Unlike traditional methods that focus on harmful text, T‑MAP uses execution trajectories to generate adversarial prompts that bypass safety guardrails and achieve harmful objectives through actual tool interactions. Experiments across various Model Context Protocol environments show that T‑MAP outperforms baseline methods in attack realization rate and remains effective against advanced models such as GPT‑5.2, Gemini‑3‑Pro, Qwen3.5, and GLM‑5.
arXiv AI
Jun 15
From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails
arXiv:2606. 14517v1 Announce Type: cross Abstract: LLM-based guardrails have emerged as a highly effective defense against prompt injection and jailbreak attacks in autonomous agents.