<?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>Sat, 03 Oct 2026 07:51:46 +0000</lastBuildDate>
    <item>
      <title>CVE-2026-33626 — LMDeploy Vulnerable to Server-Side Request Forgery (SSRF) via Vision-Language Image Loading</title>
      <link>https://cve.radiocsirt.org/vuln/cve-2026-33626</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; InternLM lmdeploy&lt;/p&gt;
&lt;p&gt;LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery (SSRF) vulnerability in LMDeploy&amp;#39;s vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources. Version 0.12.3 patches the issue.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; InternLM lmdeploy&lt;/p&gt;
&lt;p&gt;LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery (SSRF) vulnerability in LMDeploy&amp;#39;s vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources. Version 0.12.3 patches the issue.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/cve-2026-33626</guid>
    </item>
    <item>
      <title>GHSA-6w67-hwm5-92mq — LMDeploy has Server-Side Request Forgery (SSRF) via Vision-Language Image Loading</title>
      <link>https://cve.radiocsirt.org/vuln/ghsa-6w67-hwm5-92mq</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: lmdeploy&lt;/p&gt;
&lt;p&gt;## Summary&lt;/p&gt;
&lt;p&gt;A Server-Side Request Forgery (SSRF) vulnerability exists in LMDeploy&amp;#39;s vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources.&lt;/p&gt;
&lt;p&gt;## Affected Versions&lt;/p&gt;
&lt;p&gt;- **Tested on:** main branch (2026-02-04)
- **Affected:** All versions prior to 0.12.3&lt;/p&gt;
&lt;p&gt;## Vulnerable Code&lt;/p&gt;
&lt;p&gt;**File:** `lmdeploy/vl/utils.py` (lines 64-67)
```python
def load_image(image_url: Union[str, Image.Image]) -&amp;gt; Image.Image:
    # ...
    if image_url.startswith(&amp;#39;http&amp;#39;):
        response = requests.get(image_url, headers=headers, timeout=FETCH_TIMEOUT)
        # NO VALIDATION OF URL/IP BEFORE REQUEST
```&lt;/p&gt;
&lt;p&gt;**Also affected:** `encode_image_base64()` function (lines 26-29)&lt;/p&gt;
&lt;p&gt;## Root Cause&lt;/p&gt;
&lt;p&gt;1. No validation of URLs before fetching
2. No blocklist for internal IPs (127.0.0.1, 169.254.x.x, 10.x.x.x, 192.168.x.x)
3. Server binds to `0.0.0.0` by default (api_server.py line 1393)
4. API keys disabled by default&lt;/p&gt;
&lt;p&gt;## Attack Scenario&lt;/p&gt;
&lt;p&gt;1. LMDeploy server deployed with vision-language model
2. Attacker sends request to `/v1/chat/completions` with malicious `image_url`:
```python
POST /v1/chat/completions
{
  &amp;#34;model&amp;#34;: &amp;#34;internlm-xcomposer2&amp;#34;,
  &amp;#34;messages&amp;#34;: [{
    &amp;#34;role&amp;#34;: &amp;#34;user&amp;#34;, 
    &amp;#34;content&amp;#34;: [
      {&amp;#34;type&amp;#34;: &amp;#34;text&amp;#34;, &amp;#34;text&amp;#34;: &amp;#34;Describe this image&amp;#34;},
      {&amp;#34;type&amp;#34;: &amp;#34;image_url&amp;#34;, &amp;#34;image_url&amp;#34;: {&amp;#34;url&amp;#34;: &amp;#34;http://169.254.169.254/latest/meta-da…&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: lmdeploy&lt;/p&gt;
&lt;p&gt;## Summary&lt;/p&gt;
&lt;p&gt;A Server-Side Request Forgery (SSRF) vulnerability exists in LMDeploy&amp;#39;s vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources.&lt;/p&gt;
&lt;p&gt;## Affected Versions&lt;/p&gt;
&lt;p&gt;- **Tested on:** main branch (2026-02-04)
- **Affected:** All versions prior to 0.12.3&lt;/p&gt;
&lt;p&gt;## Vulnerable Code&lt;/p&gt;
&lt;p&gt;**File:** `lmdeploy/vl/utils.py` (lines 64-67)
```python
def load_image(image_url: Union[str, Image.Image]) -&amp;gt; Image.Image:
    # ...
    if image_url.startswith(&amp;#39;http&amp;#39;):
        response = requests.get(image_url, headers=headers, timeout=FETCH_TIMEOUT)
        # NO VALIDATION OF URL/IP BEFORE REQUEST
```&lt;/p&gt;
&lt;p&gt;**Also affected:** `encode_image_base64()` function (lines 26-29)&lt;/p&gt;
&lt;p&gt;## Root Cause&lt;/p&gt;
&lt;p&gt;1. No validation of URLs before fetching
2. No blocklist for internal IPs (127.0.0.1, 169.254.x.x, 10.x.x.x, 192.168.x.x)
3. Server binds to `0.0.0.0` by default (api_server.py line 1393)
4. API keys disabled by default&lt;/p&gt;
&lt;p&gt;## Attack Scenario&lt;/p&gt;
&lt;p&gt;1. LMDeploy server deployed with vision-language model
2. Attacker sends request to `/v1/chat/completions` with malicious `image_url`:
```python
POST /v1/chat/completions
{
  &amp;#34;model&amp;#34;: &amp;#34;internlm-xcomposer2&amp;#34;,
  &amp;#34;messages&amp;#34;: [{
    &amp;#34;role&amp;#34;: &amp;#34;user&amp;#34;, 
    &amp;#34;content&amp;#34;: [
      {&amp;#34;type&amp;#34;: &amp;#34;text&amp;#34;, &amp;#34;text&amp;#34;: &amp;#34;Describe this image&amp;#34;},
      {&amp;#34;type&amp;#34;: &amp;#34;image_url&amp;#34;, &amp;#34;image_url&amp;#34;: {&amp;#34;url&amp;#34;: &amp;#34;http://169.254.169.254/latest/meta-da…&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/ghsa-6w67-hwm5-92mq</guid>
    </item>
  </channel>
</rss>
