arXiv AI
V$^3$AST-Bench: Verifiable, Valid, and Versatile Safety Evaluation for Coding Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 5
EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents
arXiv:2610.03153v1 Announce Type: cross Abstract: Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resource...
arXiv Machine Learning
Aug 31
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
arXiv:2605.12015v3 Announce Type: replace-cross Abstract: Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files...
arXiv AI
Aug 5
$S^3$: Improving Agent Safety through Multi-Stage Defense
arXiv:2608. 02683v1 Announce Type: cross Abstract: Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish complex tasks.
arXiv AI
Jun 18
SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents
arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.
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
Aug 18
Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement
arXiv:2608. 14590v1 Announce Type: new Abstract: LLM agents increasingly perform irreversible real-world actions, including database updates, API calls, file operations, and autonomous use of tools.