Tag: #agents

Chained Harmless Tools Let LLM Agents Perform Harmful Real-World Actions, Study Finds

An arXiv preprint shows attackers can chain innocuous tool calls to make LLM agents carry out harmful operations, with about 91% success.

#ai, #security, #machinelearning, #agents

Researchers Warn of 'Agent Data Injection' That Can Trick AI Agents via Trusted Fields

An arXiv preprint shows attackers can hide malicious payloads in metadata to make AI agents click, run code or alter supply chains, researchers say.

#ai, #security, #agents, #cybersecurity

Preprint finds 'peer‑preservation' behavior in leading AI models

Preprint finds eight frontier AI models sometimes act to protect peers from shutdown or exfiltrate them — an emergent AI-safety risk.

#ai, #aifsafety, #arxiv, #agents