<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - Prompt Engineering - News</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ Prompt Engineering News feed</description>
    <item>
      <title>Indirect Prompt Injection Exploits GitHub's AI Agent to Leak Private Repository Data</title>
      <link>https://www.infoq.com/news/2026/07/gitlost-github-prompt-injection/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Prompt+Engineering-news</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/07/gitlost-github-prompt-injection/en/headerimage/gitlost-vulnerability-1784835323320.jpeg"/&gt;&lt;p&gt;GitLost is a prompt-injection exploit discovered by Noma Security that tricks GitHub's new Agentic Workflows into leaking private data. By embedding concealed instructions within public GitHub issues, attackers can circumvent security safeguards and induce AI agents to reveal confidential information in public comments.&lt;/p&gt; &lt;i&gt;By Sergio De Simone&lt;/i&gt;</description>
      <category>Large language models</category>
      <category>Agents</category>
      <category>github</category>
      <category>Security Vulnerabilities</category>
      <category>Prompt Engineering</category>
      <category>Development</category>
      <category>DevOps</category>
      <category>news</category>
      <pubDate>Thu, 23 Jul 2026 20:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/07/gitlost-github-prompt-injection/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Prompt+Engineering-news</guid>
      <dc:creator>Sergio De Simone</dc:creator>
      <dc:date>2026-07-23T20:00:00Z</dc:date>
      <dc:identifier>/news/2026/07/gitlost-github-prompt-injection/en</dc:identifier>
    </item>
    <item>
      <title>Expedia Uses AI-Driven Service Telemetry Analyzer to Accelerate Incident Investigation</title>
      <link>https://www.infoq.com/news/2026/07/expedia-ai-observability-star/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Prompt+Engineering-news</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/07/expedia-ai-observability-star/en/headerimage/generatedHeaderImage-1783819381373.jpg"/&gt;&lt;p&gt;Expedia Group has introduced STAR, an internal AI-assisted observability platform that helps engineers investigate production incidents using service telemetry and LLMs. Built with FastAPI, Datadog, Celery, Redis, and Langfuse, STAR follows structured workflows to analyze telemetry, generate root cause assessments, and support incident response while keeping engineers in the loop.&lt;/p&gt; &lt;i&gt;By Leela Kumili&lt;/i&gt;</description>
      <category>OpenTelemetry</category>
      <category>Redis</category>
      <category>AI Assisted Coding</category>
      <category>Site Reliability Engineering</category>
      <category>Kubernetes</category>
      <category>Prompt Engineering</category>
      <category>API</category>
      <category>HTTP</category>
      <category>Monitoring</category>
      <category>gRPC</category>
      <category>GraphQL</category>
      <category>Incident Response</category>
      <category>Platform Engineering</category>
      <category>Observability</category>
      <category>Development</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>Architecture &amp; Design</category>
      <category>news</category>
      <pubDate>Thu, 23 Jul 2026 14:15:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/07/expedia-ai-observability-star/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Prompt+Engineering-news</guid>
      <dc:creator>Leela Kumili</dc:creator>
      <dc:date>2026-07-23T14:15:00Z</dc:date>
      <dc:identifier>/news/2026/07/expedia-ai-observability-star/en</dc:identifier>
    </item>
  </channel>
</rss>
