<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Secret-Redaction on CuraSec</title><link>https://curasec.metacog.co.kr/tags/secret-redaction/</link><description>Recent content in Secret-Redaction on CuraSec</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 17 Sep 2026 15:32:45 +0000</lastBuildDate><atom:link href="https://curasec.metacog.co.kr/tags/secret-redaction/index.xml" rel="self" type="application/rss+xml"/><item><title>CosyRedactGateway: OSS secret-redaction proxy for LLM APIs</title><link>https://curasec.metacog.co.kr/insights/2026-09-17-cassiopeiacode-cosyredactgateway-77/</link><pubDate>Thu, 17 Sep 2026 15:32:45 +0000</pubDate><guid>https://curasec.metacog.co.kr/insights/2026-09-17-cassiopeiacode-cosyredactgateway-77/</guid><description>&lt;ul>
&lt;li>&lt;strong>Engineer — Learn:&lt;/strong> If you pipe internal data through OpenAI or Anthropic APIs, this stateless proxy pattern is worth evaluating as a DLP layer; no active exploit pressure, but the architecture addresses a real secret-leakage risk in LLM-integrated pipelines.&lt;/li>
&lt;li>&lt;strong>SOC/IR — Skip&lt;/strong>&lt;/li>
&lt;li>&lt;strong>Leader — Skip&lt;/strong>&lt;/li>
&lt;/ul></description></item></channel></rss>