<?xml version='1.0' encoding='UTF-8'?>
<?xml-stylesheet href="/static/style.xsl" type="text/xsl"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
  <id>https://vulnerability.circl.lu/rss/recent/all/10</id>
  <title>Most recent entries from all</title>
  <updated>2026-10-02T15:08:08.433004+00:00</updated>
  <author>
    <name>Vulnerability-Lookup</name>
    <email>info@circl.lu</email>
  </author>
  <link href="https://vulnerability.circl.lu" rel="alternate"/>
  <generator uri="https://lkiesow.github.io/python-feedgen" version="1.0.0">python-feedgen</generator>
  <subtitle>Contains only the most 10 recent entries.</subtitle>
  <entry>
    <id>https://vulnerability.circl.lu/vuln/brew-openclaw-cli-cve-2026-32898</id>
    <title>BREW-openclaw-cli-CVE-2026-32898 — OpenClaw ACP client has permission auto-approval bypass via untrusted tool metadata</title>
    <updated>2026-10-02T15:08:08.619221+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> Homebrew: openclaw-cli</p>
<p>## Vulnerability Summary</p>
<p>The OpenClaw ACP client could auto-approve tool calls based on untrusted metadata and permissive name heuristics. A malicious or compromised ACP tool invocation could bypass expected interactive approval prompts for read-class operations.</p>
<p>## Affected Packages / Versions</p>
<p>- Package: npm `openclaw`
- Affected published versions: `&lt;= 2026.2.22-2` (latest published as of February 24, 2026 is `2026.2.22-2`)
- Patched in code on `main`: `2026.2.23` (released)</p>
<p>## Technical Details</p>
<p>- Permission classification trusted incoming `toolCall.kind` and heuristic name matching.
- Non-core read-like names and spoofed kind metadata could reach auto-approve paths.
- `read` operations were not scoped strongly enough to cwd in all metadata/title forms.</p>
<p>## Fix</p>
<p>- Require trusted core tool IDs for auto-approval and ignore untrusted `toolCall.kind` as an authorization source.
- Scope `read` auto-approval to cwd-resolved paths.
- Add stricter tool-name validation and regression coverage for spoofed kind and non-core read-like names.</p>
<p>## Affected Functions</p>
<p>- `resolvePermissionRequest`
- `resolveToolNameForPermission`
- `shouldAutoApproveToolCall`</p>
<p>## Fix Commit(s)</p>
<p>- `12cc754332f9a7c92e158ce7644aa22df79c0904`
- `63dcd28ae0be2de1c75af09cc81841cebeec068f`</p>
<p>Found using [MCPwner](https://github.com/Pigyon/MCPwner)</p>
<p>Thanks @nedlir for reporting.</p></div>
    </content>
    <link href="https://vulnerability.circl.lu/vuln/brew-openclaw-cli-cve-2026-32898"/>
  </entry>
  <entry>
    <id>https://vulnerability.circl.lu/vuln/cve-2026-32898</id>
    <title>CVE-2026-32898 — OpenClaw &lt; 2026.2.23 - ACP Permission Auto-Approval Bypass via Untrusted Tool Metadata</title>
    <updated>2026-10-02T15:08:08.619380+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> OpenClaw</p>
<p>OpenClaw versions prior to 2026.2.23 contain an authorization bypass vulnerability in the ACP client that auto-approves tool calls based on untrusted toolCall.kind metadata and permissive name heuristics. Attackers can bypass interactive approval prompts for read-class operations by spoofing tool metadata or using non-core read-like names to reach auto-approve paths.</p></div>
    </content>
    <link href="https://vulnerability.circl.lu/vuln/cve-2026-32898"/>
  </entry>
</feed>
