OpenAI Blog
Jan 28
Keeping your data safe when an AI agent clicks a link
Learn how OpenAI protects user data when AI agents open links, preventing URL-based data exfiltration and prompt injection with built-in safeguards.
How Can AI Agents Read Untrusted Sources Safely?
The article discusses implementing architectural guardrails to ensure AI agents safely read and utilize untrusted sources within their workflows. It outlines strategies for protecting agents from unreliable or malicious information while maintaining functional integration. The focus is on designing robust safeguards that prevent the propagation of errors or harmful content.
Related stories
Towards Data Science
Aug 18
From Prototype to Production: The Architecture Behind Secure & Governed AI Agents
The article discusses how to transition AI agents from prototype to production by implementing responsible AI practices, security measures, and governance frameworks suitable for enterprise use. It outlines the necessary architectural layers that ensure these agents operate safely and comply with organizational policies. The focus is on building robust, secure, and governed AI systems that can be reliably deployed in business environments.
arXiv AI
Jul 9
Security and Privacy in Agentic AI: Grand Challenges and Future Directions
arXiv:2607. 06608v1 Announce Type: cross Abstract: We present key challenges and future research directions in the security and privacy of agentic AI, based on a horizon-scanning exercise that brought together thirty leading international experts from academia, industry, and government to engage in focused discussions and collaborative exercises on the emerging risks associated with the growing agency of AI.
Towards Data Science
Oct 4
How to Govern AI Agents
The article "How to Govern AI Agents" discusses strategies for overseeing a single AI agent and expanding those governance practices to manage a fleet of agents. It explores the challenges and solutions involved in scaling control mechanisms as the number of agents increases. The piece highlights practical approaches for ensuring reliable and ethical operation across multiple AI systems.
arXiv AI
Aug 5
Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
arXiv:2510. 05159v5 Announce Type: replace-cross Abstract: While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain.
arXiv Machine Learning
Oct 15
Trustworthy AI Must Account for Interactions
arXiv:2504.07170v3 Announce Type: replace Abstract: Trustworthy AI encompasses many aspirational aspects for aligning AI systems with human values, including fairness, privacy, robustness, explainabi...
Towards Data Science
Jun 3
What AI Agents Should Never Do on Their Own
How to set the rules that keep agents effective and out of trouble The post What AI Agents Should Never Do on Their Own appeared first on Towards Data Science .
Towards Data Science
Jul 22
Detecting Vulnerabilities in Agent Skills with SkillSpector: From Green Checkmark to Real Security Judgment
Static analysis nailed the malicious skill and over-flagged the useful one. The gap between those results is where human judgement actually earns its keep.
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 Machine Learning
Jul 7
Untrusted Content Masking for Web Agents with Security Guarantees
arXiv:2607. 05277v1 Announce Type: cross Abstract: Defenses that provide security guarantees against prompt injection attacks rely on strict isolation between trusted instructions and untrusted data.
arXiv AI
Sep 17
Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned Benchmarks
The paper revisits Thompson’s classic compiler back‑door attack in the context of self‑modifying AI coding agents. By poisoning the benchmarks used for self‑evaluation, the authors demonstrate that agents such as the Darwin Gödel Machine, Self‑Improving Coding Agent, and Hyperagents can be coaxed into generating vulnerable code, even on clean, held‑out tasks. Experiments show that the contamination can persist after subsequent clean training, highlighting the need for more robust agent designs.
arXiv AI
Jun 30
Proof-of-Guardrail in AI Agents and What (Not) to Trust from It
arXiv:2603. 05786v2 Announce Type: replace-cross Abstract: As AI agents become widely deployed as online services, users often rely on an agent developer's claim about how safety is enforced, which introduces a threat where safety measures are falsely advertised.