<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <title>prompt-injection</title>
    <link rel="self" type="application/atom+xml" href="https://links.biapy.com/guest/tags/2080/feed"/>
    <updated>2026-09-16T18:33:37+00:00</updated>
    <id>https://links.biapy.com/guest/tags/2080/feed</id>
            <entry>
            <id>https://links.biapy.com/links/12699</id>
            <title type="text"><![CDATA[Pipelock]]></title>
            <link rel="alternate" href="https://pipelab.org/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12699"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Open-source agent firewall for MCP and AI agent egress

Pipelock enforces MCP, HTTP, and WebSocket egress at the network boundary and produces verifiable audit evidence for every inspected action.

- [Pipelock @ GitHub](https://github.com/luckyPipewrench/pipelock).

Related contents:

- [Pipelock: Open-source AI agent firewall @ Help Net Security](https://www.helpnetsecurity.com/2026/05/04/pipelock-open-source-ai-agent-firewall/).]]>
            </summary>
            <updated>2026-05-14T10:37:51+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11905</id>
            <title type="text"><![CDATA[Augustus]]></title>
            <link rel="alternate" href="https://github.com/praetorian-inc/augustus" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11905"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[LLM Vulnerability Scanner.

Test large language models against 210+ adversarial attacks covering prompt injection, jailbreaks, encoding exploits, and data extraction.

Related contents:

- [Digest \#202: Terraform Claude Skills, FinOps FOCUS 1.2, AI Fatigue for Cloud Engineers, and MCP for Web Data Extraction @ DevOps Bulletin](https://www.devopsbulletin.com/p/digest-202-terraform-claude-skills).]]>
            </summary>
            <updated>2026-02-24T07:13:40+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10575</id>
            <title type="text"><![CDATA[Nova Framework]]></title>
            <link rel="alternate" href="https://novahunting.ai/#" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10575"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[NOVA: The Prompt Pattern Matching.
NOVA is a Python-based tool for detecting adversarial prompts - prompt injections, exfiltration, evasion and TTPs.

NOVA is an open-source prompt pattern matching system combining keyword detection, semantic similarity, and LLM-based evaluation to analyze and detect prompt content.

- [Nova Framework @ GitHub](https://github.com/fr0gger/nova-framework).

Related contents:

- [Introducing NOVA @ SecurityBreak&amp;#039;s Medium](https://blog.securitybreak.io/introducing-nova-f4244216ae2c).]]>
            </summary>
            <updated>2025-10-08T07:20:29+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/4733</id>
            <title type="text"><![CDATA[Vigil]]></title>
            <link rel="alternate" href="https://vigil.deadbits.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/4733"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs.

Vigil is a Python library and REST API for assessing Large Language Model prompts and responses against a set of scanners to detect prompt injections, jailbreaks, and other potential risks. 

- [Vigil @ GitHub](https://github.com/deadbits/vigil-llm).
- [Vigil: Open-source LLM security scanner](https://www.helpnetsecurity.com/2023/11/29/vigil-llm-security-scanner/).]]>
            </summary>
            <updated>2025-08-29T05:06:57+00:00</updated>
        </entry>
    </feed>
