arXiv AI
Jul 28
Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls
arXiv:2607. 24343v1 Announce Type: cross Abstract: Language-model agents act through structured tool calls whose arguments carry different risks.
Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls
Language-model agents act through structured tool calls whose arguments carry different risks. Untrusted content may safely influence an email body but should not determine a recipient, account, command, or credential.
Related stories
arXiv AI
Jun 2
When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
arXiv:2606. 00448v1 Announce Type: cross Abstract: LLM agents increasingly rely on community-contributed skills that expand an agent's operational capability set.
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
Jun 16
SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills
arXiv:2606. 15899v1 Announce Type: cross Abstract: Open-source LLM agent ecosystems are growing rapidly, yet the security of community-contributed skills - modular tool definitions that extend agent capabilities - remains largely unvetted.
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
Jul 9
Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents
arXiv:2607. 07474v1 Announce Type: cross Abstract: Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not.
arXiv AI
Jun 2
AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations
arXiv:2606. 02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls.
arXiv AI
Jun 16
Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems
arXiv:2606. 15242v1 Announce Type: cross Abstract: Skills are becoming the capability layer through which LLM agents turn plans into actions, but their use introduces security risks such as data leakage, unauthorized operations, and tool misuse.
arXiv AI
Jul 31
The Capability Paradox: How Smarter Auditors Make Multi-Agent Systems Less Secure
arXiv:2605. 17480v3 Announce Type: replace Abstract: Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces.
arXiv AI
Aug 3
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents
arXiv:2607. 29254v1 Announce Type: new Abstract: AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential real-world actions.
arXiv AI
Jul 1
A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems
arXiv:2606. 31639v1 Announce Type: cross Abstract: Large language models are no longer only text generators.
arXiv AI
Jul 29
Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales
arXiv:2607. 25364v1 Announce Type: new Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales.