Security Considerations for Artificial Intelligence Agents
This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by Perplexity's experience operating general-purpose agentic systems used by millions of users and thousands of enterprises in both controlled and open-world environments. Agent architectures change core assumptions around code-data separation, authority boundaries,
Record details
Published: 12 March 2026
Source: arXiv
Category: Research
Topics: Agents & autonomy · Environment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Energy IT shop not interested in Grok, Perplexity as its AI portfolio expands
FedScoop · 10 July 2026
Perplexity launches secure sandbox to make its AI agents secure and powerful
SiliconANGLE AI · 15 July 2026
I gave Perplexity's agentic AI 5 complex tasks to run on my Mac - and I'll do it again
ZDNet AI · 22 July 2026
Perplexity’s Personal Computer turns Windows PCs into AI agents
The Verge · 28 July 2026
Perplexity brings its Personal Computer AI agent to Windows
SiliconANGLE AI · 28 July 2026
“Stateful systems are incredibly hard to build”: How Perplexity thinks about AI agent sandboxes
The New Stack AI · 29 July 2026
How to cite this record
ethics.ai (12 March 2026), “Security Considerations for Artificial Intelligence Agents,” evidence record 7316, https://ethics.ai/record/7316 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.