SentinelOne launches Singularity Agentic Detection and Response
Original title: SentinelOne brings runtime threat detection and response to AI agents
The add-on inventories agents and MCP servers, blocks prompt injection and jailbreaks inline, and can stop one agent without halting a workflow.
SentinelOne unveiled Singularity Agentic Detection and Response on the Singularity Platform to discover AI agents, limit what they can reach, and stop malicious or unintended actions at runtime. Named coverage includes Salesforce Agentforce, Microsoft Copilot Studio, OpenAI ChatGPT workspace agents, and Anthropic Claude managed agents. Agent Traces go to Singularity Data Lake and are linked with endpoint behavior in one Storyline graph. The company says it extends Prompt AI Agent Security, introduced in March.
- Inline controls target prompt injection, jailbreaks, credential exfiltration, and tool poisoning.
- Intent-drift detection compares the requested task with what the agent actually did.
- Inventory covers agents, tools, skills, connectors, and MCP servers, sanctioned or not.
- SentinelOne says the platform is already used by over 15,000 customers and partners.
- Vendors
- SentinelOne
From the original article
4 min read at helpnetsecurity.comSentinelOne has unveiled Singularity Agentic Detection and Response (ADR), a new offering that discovers AI agents, enforces what agents are allowed to do, monitors agent behavior in depth, and detects and stops unintended and malicious activity in real time.
By Industry News · helpnetsecurity.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.