arXiv:2607. 24343v1 Announce Type: cross Abstract: Language-model agents act through structured tool calls whose arguments carry different risks.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
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.
arXiv:2606. 00448v1 Announce Type: cross Abstract: LLM agents increasingly rely on community-contributed skills that expand an agent's operational capability set.
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: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.
arXiv:2608. 17597v1 Announce Type: cross Abstract: Large language models are increasingly deployed through agent harnesses that manage tools, extensions, persistent state, permissions, and external actions.
arXiv:2608. 17588v1 Announce Type: new Abstract: Agent Skills package reusable natural language procedures with executable resources, enabling software agents to acquire task specific capabilities without model adaptation.