<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <title>llm-security</title>
    <link rel="self" type="application/atom+xml" href="https://links.biapy.com/guest/tags/3502/feed"/>
    <updated>2026-09-20T23:00:12+00:00</updated>
    <id>https://links.biapy.com/guest/tags/3502/feed</id>
            <entry>
            <id>https://links.biapy.com/links/13668</id>
            <title type="text"><![CDATA[Agent-Safe Pipeline]]></title>
            <link rel="alternate" href="https://github.com/decionis/agent-safe-pipeline" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13668"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), verified human approval, and a SafeExecutor that consumes a single-use intent-bound grant.]]>
            </summary>
            <updated>2026-08-17T09:32:57+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13538</id>
            <title type="text"><![CDATA[ADR: Agentic AI Detection and Response]]></title>
            <link rel="alternate" href="https://github.com/uber/ADR" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13538"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

ADR (Agentic AI Detection and Response) is an enterprise security system for AI agents. It helps organizations secure employee-facing agents such as Cursor, Claude Code, and Codex, as well as customer-facing agents such as AI support agents.]]>
            </summary>
            <updated>2026-08-05T11:46:32+00:00</updated>
        </entry>
    </feed>
