CVE-2026-44335Critical· 9.8▾ Midnight

PraisonAI has an SSRF bypass

▾ Midnight zone — Critical, or high with PoC / in-the-wild

Depth score54/ 100 · Moderate

impact 53.9 · likelihood 0.1 · exploitation 0

⚡ Agent-ready:Raw markdown ↗JSON ↗

Proof of concept

Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.

…

Published

May 6, 2026

Updated

Jul 13, 2026

CVSS

9.8

Vendor

praisonaiagents

Product

praisonaiagents

CWE

—

Depth score

54 · Moderate

EPSS

0.38% · p32

Platforms

—

Source

OSV

Vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

EPSS history

Exploit-prediction probability, daily snapshots since Jul 13.

0.4% → 0.4%

Timeline

Disclosure to exploitation, from the record and what we observed since indexing it.

3 events · 68 days

May 6, 2026Published
Disclosed via OSV
Jul 13, 2026Record revised
Last analysed / modified upstream
Jul 13, 2026EPSS first tracked
0.4%

praisonaiagents #osv #pip

Affected

praisonaiagents < 1.6.32

Patched in

praisonaiagents 1.6.32

Full technical detail▾

Overview

Summary

The URL checking logic in PraisonAI has a logical flaw that could be bypassed by attackers, leading to SSRF attacks.

Details

The current PraisonAI project uses _validate_url to validate the input URL. The main logic is to perform security checks on the host portion of the URL extracted by urlparse to prevent SSRF attacks.

However, there are indeed differences in parsing between urlparse and the library that actually sends the request. Currently, almost all application scenarios in this project involve first using _validate_url for URL validation, and then using _get_session().get to send the request.

In reality, its underlying mechanism is requests.get.

The core issue: urlparse() and requests disagree on which host a URL like http://127.0.0.1:6666\@1.1.1.1 points to:

urlparse() treats \ as a regular character and @ as the userinfo-host delimiter, so it extracts hostname as 1.1.1.1 (public)
requests treats \ as a path character, connecting to 127.0.0.1 (internal)

Below is a test code I wrote following the code.

import sys
from pathlib import Path
from pprint import pprint

sys.path.insert(0, str(Path(r"D:/BaiduNetdiskDownload/PraisonAI-main/PraisonAI-main/src/praisonai-agents")))

from praisonaiagents.tools import spider_tools

# url = "http://127.0.0.1:6666\@1.1.1.1"
url = "http://127.0.0.1:6666"

result = spider_tools.scrape_page(url)

if isinstance(result, dict) and "error" in result:
    print("scrape failed:", result["error"])
else:
    pprint(result)

When an attacker uses http://127.0.0.1:6666/, the existing detection logic can detect that this is an internal network address and block it.

However, when an attacker uses http://127.0.0.1:6666\@1.1.1.1, the detection logic resolves the host to 1.1.1.1, which is a public IP address, thus passing the verification. But in the actual request process, this URL is forwarded by requests.get to http://127.0.0.1:6666, bypassing the detection and achieving an SSRF attack.

PoC

http://127.0.0.1:6666\@1.1.1.1

Impact

SSRF

Affected packages

praisonaiagents < 1.6.32

Remediation

Upgrade to a patched release:

praisonaiagents 1.6.32

References

Related vulnerabilities

Connected by shared product, vendor, weakness, or advisory.

#osv#pip

Overview

Summary

The URL checking logic in PraisonAI has a logical flaw that could be bypassed by attackers, leading to SSRF attacks.

Details

The current PraisonAI project uses _validate_url to validate the input URL. The main logic is to perform security checks on the host portion of the URL extracted by urlparse to prevent SSRF attacks.

In reality, its underlying mechanism is requests.get.

The core issue: urlparse() and requests disagree on which host a URL like http://127.0.0.1:6666\@1.1.1.1 points to:

urlparse() treats \ as a regular character and @ as the userinfo-host delimiter, so it extracts hostname as 1.1.1.1 (public)

requests treats \ as a path character, connecting to 127.0.0.1 (internal)

Below is a test code I wrote following the code.

import sys from pathlib import Path from pprint import pprint sys.path.insert(0, str(Path(r"D:/BaiduNetdiskDownload/PraisonAI-main/PraisonAI-main/src/praisonai-agents"))) from praisonaiagents.tools import spider_tools # url = "http://127.0.0.1:6666\@1.1.1.1" url = "http://127.0.0.1:6666" result = spider_tools.scrape_page(url) if isinstance(result, dict) and "error" in result: print("scrape failed:", result["error"]) else: pprint(result)

When an attacker uses http://127.0.0.1:6666/, the existing detection logic can detect that this is an internal network address and block it.

PoC

http://127.0.0.1:6666\@1.1.1.1

Impact

SSRF