<?xml version='1.0' encoding='UTF-8'?>
<?xml-stylesheet href="/static/style.xsl" type="text/xsl"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
  <channel>
    <title>Most recent entries from all</title>
    <link>https://cve.radiocsirt.org</link>
    <description>Contains only the most 10 recent entries.</description>
    <docs>http://www.rssboard.org/rss-specification</docs>
    <generator>python-feedgen</generator>
    <language>en</language>
    <lastBuildDate>Sun, 22 Nov 2026 21:21:47 +0000</lastBuildDate>
    <item>
      <title>EUVD-2026-409047</title>
      <link>https://cve.radiocsirt.org/vuln/euvd-2026-409047</link>
      <description>EUVD-2026-409047</description>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/euvd-2026-409047</guid>
    </item>
    <item>
      <title>fkie_cve-2026-75518</title>
      <link>https://cve.radiocsirt.org/vuln/fkie_cve-2026-75518</link>
      <description>&lt;p&gt;DOMShell is a Chrome automation project whose MCP server exposes Unix-style tools for AI agents. Prior to 2.0.8, the DOMShell MCP server classifies the domshell_eval tool and eval command as read-tier operations that can run without --allow-write, even though eval shares the Runtime.evaluate dispatch path with the write-tier js command and has no side-effect gate. An MCP caller with tool-session access can therefore use domshell_eval to mutate DOM, window, or global state while the host approval interface, server authorization flags, denial messages, and audit records represent the operation as read-only. The bypass does not expose a capability beyond domshell_js for callers already authorized to write, but it violates the configured permission boundary for callers lacking that authorization. This issue is fixed in version 2.0.8.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;DOMShell is a Chrome automation project whose MCP server exposes Unix-style tools for AI agents. Prior to 2.0.8, the DOMShell MCP server classifies the domshell_eval tool and eval command as read-tier operations that can run without --allow-write, even though eval shares the Runtime.evaluate dispatch path with the write-tier js command and has no side-effect gate. An MCP caller with tool-session access can therefore use domshell_eval to mutate DOM, window, or global state while the host approval interface, server authorization flags, denial messages, and audit records represent the operation as read-only. The bypass does not expose a capability beyond domshell_js for callers already authorized to write, but it violates the configured permission boundary for callers lacking that authorization. This issue is fixed in version 2.0.8.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/fkie_cve-2026-75518</guid>
    </item>
    <item>
      <title>GHSA-vg83-hcp4-5qcc — DOMShell: domshell_eval classified as read-tier can execute side-effecting JavaScript without --allow-write</title>
      <link>https://cve.radiocsirt.org/vuln/ghsa-vg83-hcp4-5qcc</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; npm: @apireno/domshell&lt;/p&gt;
&lt;p&gt;### Summary&lt;/p&gt;
&lt;p&gt;The `domshell_eval` MCP tool (and the `eval` command inside `domshell_execute`) was classified as **read-tier**, allowing it to run without the `--allow-write` server flag. However, `eval` and the write-tier `js` command dispatch to the same handler in the extension and call CDP `Runtime.evaluate` with the raw expression string and no side-effect gate. Any JavaScript expression could therefore mutate DOM, window, or global state through `domshell_eval` without the operator&amp;#39;s `--allow-write` authorization.&lt;/p&gt;
&lt;p&gt;The tool description explicitly promised &amp;#34;(read-only) ... always available in read-only mode&amp;#34; — the misclassification contradicted the documented contract, not just an implicit one.&lt;/p&gt;
&lt;p&gt;### Impact&lt;/p&gt;
&lt;p&gt;No new capability was exposed — the same write access was already available via `domshell_js` with `--allow-write` — but the tier misclassification meant:&lt;/p&gt;
&lt;p&gt;- MCP hosts (Claude Desktop, Cursor, etc.) rendered the wrong approval UI (`readOnlyHint: true`)
- Server-side tier flags (`--allow-write`) misrepresented what an AI agent was actually authorized to do
- Audit logs and deny messages labeled write-tier activity as read-tier
- Downstream tools and analysis relying on the tier separation could over-trust an `eval` call&lt;/p&gt;
&lt;p&gt;Framing: OWASP LLM Top 10 LLM06 (Excessive Agency), NIST AI RMF (tool permission boundary + human-approval fidelity), CWE-863 (Incorrect Authorization).&lt;/p&gt;
&lt;p&gt;The reporter&amp;#39;s main framing: **the MCP approval UI and server-side permission model can misrepresen…&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; npm: @apireno/domshell&lt;/p&gt;
&lt;p&gt;### Summary&lt;/p&gt;
&lt;p&gt;The `domshell_eval` MCP tool (and the `eval` command inside `domshell_execute`) was classified as **read-tier**, allowing it to run without the `--allow-write` server flag. However, `eval` and the write-tier `js` command dispatch to the same handler in the extension and call CDP `Runtime.evaluate` with the raw expression string and no side-effect gate. Any JavaScript expression could therefore mutate DOM, window, or global state through `domshell_eval` without the operator&amp;#39;s `--allow-write` authorization.&lt;/p&gt;
&lt;p&gt;The tool description explicitly promised &amp;#34;(read-only) ... always available in read-only mode&amp;#34; — the misclassification contradicted the documented contract, not just an implicit one.&lt;/p&gt;
&lt;p&gt;### Impact&lt;/p&gt;
&lt;p&gt;No new capability was exposed — the same write access was already available via `domshell_js` with `--allow-write` — but the tier misclassification meant:&lt;/p&gt;
&lt;p&gt;- MCP hosts (Claude Desktop, Cursor, etc.) rendered the wrong approval UI (`readOnlyHint: true`)
- Server-side tier flags (`--allow-write`) misrepresented what an AI agent was actually authorized to do
- Audit logs and deny messages labeled write-tier activity as read-tier
- Downstream tools and analysis relying on the tier separation could over-trust an `eval` call&lt;/p&gt;
&lt;p&gt;Framing: OWASP LLM Top 10 LLM06 (Excessive Agency), NIST AI RMF (tool permission boundary + human-approval fidelity), CWE-863 (Incorrect Authorization).&lt;/p&gt;
&lt;p&gt;The reporter&amp;#39;s main framing: **the MCP approval UI and server-side permission model can misrepresen…&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/ghsa-vg83-hcp4-5qcc</guid>
    </item>
  </channel>
</rss>
