arXiv Machine Learning
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
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
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.
Hugging Face Trending Papers
Jul 22
OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills
LLM-based agents leverage third-party skills to extend their capabilities in open-world scenarios. However, third-party skills can introduce extra security vulnerabilities, as seemingly harmless skills can contain latent safety risks that only emerge during actual execution.
arXiv AI
Oct 1
Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents
arXiv:2609.39065v1 Announce Type: cross Abstract: LLM agents increasingly rely on installable skills, which are packages of instructions, code, and resources that equip them with task-specific capabi...
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 AI
Sep 28
Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems
The paper introduces skill cascading attacks, where a malicious goal is spread across multiple seemingly benign skills, causing harmful outcomes when combined. It presents SkillCascade, an automated red‑teaming framework, and releases SkillCascade‑Bench, a benchmark of 213 validated cascading test cases across various agent systems and domains. Experiments show that these cascaded interactions reliably induce harmful behaviors while evading existing per‑skill scanners and runtime monitors, revealing a gap between component‑level integrity and system‑level safety.