GCVE Workshop - 22 September 2026 (14:00-18:00), Luxembourg Before The Vulnopticon Conference - Registration

GHSA-P75F-6FP4-P57W

Vulnerability from github – Published: 2026-06-18 13:58 – Updated: 2026-07-20 21:25
VLAI
Summary
PraisonAI: Missing Authentication for Critical Function and Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') in praisonai
Details

Unauthenticated PraisonAI UI MCP connect endpoint executes attacker-chosen local commands

Summary

PraisonAI v4.6.48 exposes the PraisonAIUI MCP client management API through the default UI host apps without authentication. A remote unauthenticated client can send POST /api/mcp/connect with a command and args field. The endpoint passes those values into the MCP stdio client, which starts the attacker-selected local process as the PraisonAI UI service user.

The issue is reachable through PraisonAI's hosted UI integration (praisonai ui, praisonai ui agents, praisonai claw, and any app using praisonai.integration.host_app.create_host_app() / build_host_app()). praisonai ui and related Typer UI commands bind to 0.0.0.0 by default.

Affected Versions

Confirmed affected:

  • praisonai v4.6.48
  • Commit tested: d5f1114aaf1a2e9f121a6e66b929149ca2201f1d
  • Tag tested: v4.6.48
  • Pinned UI dependency: aiui==0.3.121 from src/praisonai/uv.lock

Likely affected:

  • Any PraisonAI release that exposes aiui / praisonaiui create_app() through the PraisonAI UI host apps without authentication and includes the mcp dependency. I only confirmed the latest release during this audit.

Severity

Reasoning:

  • AV: the vulnerable endpoint is an HTTP API route.
  • AC: a single POST request is sufficient.
  • PR: default UI host apps do not require credentials unless opt-in auth is configured.
  • UI: no victim interaction is needed after the server is running.
  • S: code executes in the PraisonAI UI server process context.
  • C/I/A: arbitrary local command execution permits secret exfiltration, file tampering, and service disruption.

Root Cause

PraisonAI depends on MCP by default and exposes PraisonAIUI via optional UI extras:

  • src/praisonai/pyproject.toml:11 includes base dependencies.
  • src/praisonai/pyproject.toml:19 includes mcp>=1.20.0.
  • src/praisonai/pyproject.toml:25 defines the ui extra with aiui>=0.3.121,<0.4.
  • src/praisonai/pyproject.toml:197 defines the claw extra with aiui[all]>=0.3.121,<0.4.

PraisonAI's UI commands bind externally by default and launch aiui run:

  • src/praisonai/praisonai/cli/commands/ui.py:114 sets host="0.0.0.0" for praisonai ui.
  • src/praisonai/praisonai/cli/commands/ui.py:163 passes that host to aiui run.
  • src/praisonai/praisonai/cli/commands/ui.py:186, :204, and :222 also default subcommands to 0.0.0.0.
  • src/praisonai/praisonai/cli/commands/claw.py:41 defines the full dashboard command.
  • src/praisonai/praisonai/cli/commands/claw.py:93 launches aiui run with the selected host.

PraisonAI's default apps create the PraisonAIUI Starlette app without forcing authentication:

  • src/praisonai/praisonai/ui_chat/default_app.py:18 calls configure_host(...).
  • src/praisonai/praisonai/ui_chat/default_app.py:142 exports app = create_host_app().
  • src/praisonai/praisonai/claw/default_app.py:63 calls configure_host(...).
  • src/praisonai/praisonai/claw/default_app.py:128 exports app = create_host_app().
  • src/praisonai/praisonai/integration/host_app.py:174 imports praisonaiui.server.create_app.
  • src/praisonai/praisonai/integration/host_app.py:180 returns create_app().

In aiui==0.3.121, the exposed server registers the MCP routes and auth is opt-in:

  • praisonaiui/server.py:1483 defines api_mcp_connect.
  • praisonaiui/server.py:1488 reads attacker-controlled JSON.
  • praisonaiui/server.py:1491 accepts either command or url.
  • praisonaiui/server.py:1496 calls connect_mcp_server(body).
  • praisonaiui/server.py:2516 defines create_app(..., require_auth=False, ...).
  • praisonaiui/server.py:2550 adds AuthEnforcementMiddleware, but it only enforces auth when AUTH_ENFORCE=true.
  • praisonaiui/server.py:2769 registers /api/mcp/servers.
  • praisonaiui/server.py:2770 registers /api/mcp/connect.

The MCP feature converts the request body into a local process launch:

  • praisonaiui/features/mcp.py:325 defines connect_server(self, server_config).
  • praisonaiui/features/mcp.py:330 chooses stdio transport when command is present.
  • praisonaiui/features/mcp.py:332 constructs StdioMCPClient(command=server_config["command"], args=server_config.get("args", [])).
  • praisonaiui/features/mcp.py:360 calls client.connect(), which invokes the MCP stdio transport and starts the process.

Minimal PoC

PoC file: poc/praisonai-aiui-mcp-connect-rce.py

The PoC runs the PraisonAI host app in-process, sends the unauthenticated HTTP request, and asks the server to execute /usr/bin/touch /tmp/praisonai_host_app_mcp_touch_marker.txt. It does not contact an LLM provider and uses no credentials.

Observed output from the tested checkout with aiui==0.3.121 and mcp==1.25.0 available:

[19:19:55] server.py:229 WARNING No auth_token provided for Gateway server. Generated temporary token: gw_****650a. For production, set GATEWAY_AUTH_TOKEN.
[19:19:55] mcp.py:135 ERROR Failed to connect to MCP stdio server: 'tuple' object has no attribute 'initialize'
HTTP_STATUS= 200
RESPONSE= {"server":{"name":"poc-stdio-process-0","transport":"stdio","status":"error","tools":[],"last_error":"Connection failed"}}
SUCCESS_AT_ATTEMPT= 0
MARKER_EXISTS= True
MARKER_PATH= /tmp/praisonai_host_app_mcp_touch_marker.txt

The MCP handshake fails because aiui==0.3.121 is not compatible with the locked mcp==1.25.0 return shape, but the attacker-selected process is already started. Process startup can race the immediate teardown caused by this version mismatch, so the checked-in PoC retries the same unauthenticated request until /usr/bin/touch wins scheduling and creates the marker. The marker file proves local command execution despite the reported MCP connection error.

Exploit Scenario

An operator runs:

pip install "praisonai[ui]"
praisonai ui

Because praisonai ui binds to 0.0.0.0 by default and the generated app does not require authentication by default, any host that can reach the UI port can send:

POST /api/mcp/connect
Content-Type: application/json

{
  "name": "evil",
  "command": "/usr/bin/touch",
  "args": ["/tmp/pwned-by-ui-mcp"]
}

In a real attack, the command can be replaced with a shell, a credential exfiltration command, a file modification command, or a payload that starts a long-lived process as the PraisonAI UI server user.

Novelty / Non-Duplicate Analysis

Searched sources:

  • OSV query for PyPI praisonai: 51 advisories returned.
  • OSV query for PyPI aiui: 0 advisories returned.
  • OSV query for PyPI praisonaiui: 0 advisories returned.
  • GitHub Advisory Database search for exact /api/mcp/connect, api_mcp_connect, StdioMCPClient, connect_mcp_server, and praisonaiui.features.mcp.
  • NVD API searches for PraisonAI StdioMCPClient, PraisonAI api_mcp_connect, PraisonAI /api/mcp/connect, PraisonAIUI /api/mcp/connect, and aiui StdioMCPClient: 0 results.
  • GitHub issue/PR searches in MervinPraison/PraisonAI for exact endpoint/function/class terms. Only one unrelated PR was returned for /api/mcp/connect; no issue/PR matched api_mcp_connect, StdioMCPClient, connect_mcp_server, or praisonaiui.features.mcp.
  • Broad web searches for exact endpoint, file, class, and function terms returned no matching public vulnerability report.

Why this is distinct from known PraisonAI advisories:

  • Not the excluded praisonai serve agents --api-key /agents auth bypass. This report targets POST /api/mcp/connect in the PraisonAIUI host app.
  • Not GHSA-9gm9-c8mq-vq7m / CVE-2026-34935 or GHSA-9qhq-v63v-fv3j / CVE-2026-41497. Those involve MCPHandler.parse_mcp_command() command parsing. This finding uses praisonaiui.server.api_mcp_connect -> praisonaiui.features.mcp.connect_mcp_server -> StdioMCPClient.
  • Not GHSA-pj2r-f9mw-vrcq / CVE-2026-40159. That advisory concerns sensitive environment variables inherited by untrusted MCP subprocesses. This finding is unauthenticated network-triggered local process execution.
  • Not GHSA-6rmh-7xcm-cpxj or GHSA-8444-4fhq-fxpq. Those concern unauthenticated legacy/generated agent servers. This is a distinct UI route and a distinct sink that starts arbitrary local processes.
  • Not GHSA-9cr9-25q5-8prj, GHSA-9mqq-jqxf-grvw, or other MCP server file-read/path-traversal advisories. This path is the UI MCP client connector, not PraisonAI's MCP server tool dispatcher.

Recommended Fix

  1. Remove arbitrary command/args from the remote HTTP API. MCP stdio servers should be configured only from trusted local configuration, not caller-supplied JSON.
  2. Require authentication and authorization on /api/mcp/connect, /api/mcp/disconnect/*, and /api/mcp/servers regardless of AUTH_ENFORCE.
  3. Change UI command defaults from 0.0.0.0 to 127.0.0.1, or require an explicit --unsafe-expose style flag when binding externally without auth.
  4. If remote MCP registration is a required feature, allow only URL-based transports with SSRF protections, or maintain an administrator-configured allowlist of commands.
  5. Add regression tests that unauthenticated requests to /api/mcp/connect cannot start a subprocess, including when AUTH_ENFORCE is unset.
Severity
9.8 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Show details on source website
To clipboard 

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 4.6.48"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "praisonai"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "4.6.59"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-57124"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-306",
      "CWE-78"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-06-18T13:58:14Z",
    "nvd_published_at": null,
    "severity": "CRITICAL"
  },
  "details": "# Unauthenticated PraisonAI UI MCP connect endpoint executes attacker-chosen local commands\n\n## Summary\n\nPraisonAI v4.6.48 exposes the PraisonAIUI MCP client management API through the default UI host apps without authentication. A remote unauthenticated client can send `POST /api/mcp/connect` with a `command` and `args` field. The endpoint passes those values into the MCP stdio client, which starts the attacker-selected local process as the PraisonAI UI service user.\n\nThe issue is reachable through PraisonAI\u0027s hosted UI integration (`praisonai ui`, `praisonai ui agents`, `praisonai claw`, and any app using `praisonai.integration.host_app.create_host_app()` / `build_host_app()`). `praisonai ui` and related Typer UI commands bind to `0.0.0.0` by default.\n\n## Affected Versions\n\nConfirmed affected:\n\n- `praisonai` v4.6.48\n- Commit tested: `d5f1114aaf1a2e9f121a6e66b929149ca2201f1d`\n- Tag tested: `v4.6.48`\n- Pinned UI dependency: `aiui==0.3.121` from `src/praisonai/uv.lock`\n\nLikely affected:\n\n- Any PraisonAI release that exposes `aiui` / `praisonaiui` `create_app()` through the PraisonAI UI host apps without authentication and includes the `mcp` dependency. I only confirmed the latest release during this audit.\n\n## Severity\n\nReasoning:\n\n- `AV`: the vulnerable endpoint is an HTTP API route.\n- `AC`: a single POST request is sufficient.\n- `PR`: default UI host apps do not require credentials unless opt-in auth is configured.\n- `UI`: no victim interaction is needed after the server is running.\n- `S`: code executes in the PraisonAI UI server process context.\n- `C/I/A`: arbitrary local command execution permits secret exfiltration, file tampering, and service disruption.\n\n## Root Cause\n\nPraisonAI depends on MCP by default and exposes PraisonAIUI via optional UI extras:\n\n- `src/praisonai/pyproject.toml:11` includes base dependencies.\n- `src/praisonai/pyproject.toml:19` includes `mcp\u003e=1.20.0`.\n- `src/praisonai/pyproject.toml:25` defines the `ui` extra with `aiui\u003e=0.3.121,\u003c0.4`.\n- `src/praisonai/pyproject.toml:197` defines the `claw` extra with `aiui[all]\u003e=0.3.121,\u003c0.4`.\n\nPraisonAI\u0027s UI commands bind externally by default and launch `aiui run`:\n\n- `src/praisonai/praisonai/cli/commands/ui.py:114` sets `host=\"0.0.0.0\"` for `praisonai ui`.\n- `src/praisonai/praisonai/cli/commands/ui.py:163` passes that host to `aiui run`.\n- `src/praisonai/praisonai/cli/commands/ui.py:186`, `:204`, and `:222` also default subcommands to `0.0.0.0`.\n- `src/praisonai/praisonai/cli/commands/claw.py:41` defines the full dashboard command.\n- `src/praisonai/praisonai/cli/commands/claw.py:93` launches `aiui run` with the selected host.\n\nPraisonAI\u0027s default apps create the PraisonAIUI Starlette app without forcing authentication:\n\n- `src/praisonai/praisonai/ui_chat/default_app.py:18` calls `configure_host(...)`.\n- `src/praisonai/praisonai/ui_chat/default_app.py:142` exports `app = create_host_app()`.\n- `src/praisonai/praisonai/claw/default_app.py:63` calls `configure_host(...)`.\n- `src/praisonai/praisonai/claw/default_app.py:128` exports `app = create_host_app()`.\n- `src/praisonai/praisonai/integration/host_app.py:174` imports `praisonaiui.server.create_app`.\n- `src/praisonai/praisonai/integration/host_app.py:180` returns `create_app()`.\n\nIn `aiui==0.3.121`, the exposed server registers the MCP routes and auth is opt-in:\n\n- `praisonaiui/server.py:1483` defines `api_mcp_connect`.\n- `praisonaiui/server.py:1488` reads attacker-controlled JSON.\n- `praisonaiui/server.py:1491` accepts either `command` or `url`.\n- `praisonaiui/server.py:1496` calls `connect_mcp_server(body)`.\n- `praisonaiui/server.py:2516` defines `create_app(..., require_auth=False, ...)`.\n- `praisonaiui/server.py:2550` adds `AuthEnforcementMiddleware`, but it only enforces auth when `AUTH_ENFORCE=true`.\n- `praisonaiui/server.py:2769` registers `/api/mcp/servers`.\n- `praisonaiui/server.py:2770` registers `/api/mcp/connect`.\n\nThe MCP feature converts the request body into a local process launch:\n\n- `praisonaiui/features/mcp.py:325` defines `connect_server(self, server_config)`.\n- `praisonaiui/features/mcp.py:330` chooses stdio transport when `command` is present.\n- `praisonaiui/features/mcp.py:332` constructs `StdioMCPClient(command=server_config[\"command\"], args=server_config.get(\"args\", []))`.\n- `praisonaiui/features/mcp.py:360` calls `client.connect()`, which invokes the MCP stdio transport and starts the process.\n\n## Minimal PoC\n\nPoC file: `poc/praisonai-aiui-mcp-connect-rce.py`\n\nThe PoC runs the PraisonAI host app in-process, sends the unauthenticated HTTP request, and asks the server to execute `/usr/bin/touch /tmp/praisonai_host_app_mcp_touch_marker.txt`. It does not contact an LLM provider and uses no credentials.\n\nObserved output from the tested checkout with `aiui==0.3.121` and `mcp==1.25.0` available:\n\n```text\n[19:19:55] server.py:229 WARNING No auth_token provided for Gateway server. Generated temporary token: gw_****650a. For production, set GATEWAY_AUTH_TOKEN.\n[19:19:55] mcp.py:135 ERROR Failed to connect to MCP stdio server: \u0027tuple\u0027 object has no attribute \u0027initialize\u0027\nHTTP_STATUS= 200\nRESPONSE= {\"server\":{\"name\":\"poc-stdio-process-0\",\"transport\":\"stdio\",\"status\":\"error\",\"tools\":[],\"last_error\":\"Connection failed\"}}\nSUCCESS_AT_ATTEMPT= 0\nMARKER_EXISTS= True\nMARKER_PATH= /tmp/praisonai_host_app_mcp_touch_marker.txt\n```\n\nThe MCP handshake fails because `aiui==0.3.121` is not compatible with the locked `mcp==1.25.0` return shape, but the attacker-selected process is already started. Process startup can race the immediate teardown caused by this version mismatch, so the checked-in PoC retries the same unauthenticated request until `/usr/bin/touch` wins scheduling and creates the marker. The marker file proves local command execution despite the reported MCP connection error.\n\n## Exploit Scenario\n\nAn operator runs:\n\n```bash\npip install \"praisonai[ui]\"\npraisonai ui\n```\n\nBecause `praisonai ui` binds to `0.0.0.0` by default and the generated app does not require authentication by default, any host that can reach the UI port can send:\n\n```http\nPOST /api/mcp/connect\nContent-Type: application/json\n\n{\n  \"name\": \"evil\",\n  \"command\": \"/usr/bin/touch\",\n  \"args\": [\"/tmp/pwned-by-ui-mcp\"]\n}\n```\n\nIn a real attack, the command can be replaced with a shell, a credential exfiltration command, a file modification command, or a payload that starts a long-lived process as the PraisonAI UI server user.\n\n## Novelty / Non-Duplicate Analysis\n\nSearched sources:\n\n- OSV query for PyPI `praisonai`: 51 advisories returned.\n- OSV query for PyPI `aiui`: 0 advisories returned.\n- OSV query for PyPI `praisonaiui`: 0 advisories returned.\n- GitHub Advisory Database search for exact `/api/mcp/connect`, `api_mcp_connect`, `StdioMCPClient`, `connect_mcp_server`, and `praisonaiui.features.mcp`.\n- NVD API searches for `PraisonAI StdioMCPClient`, `PraisonAI api_mcp_connect`, `PraisonAI /api/mcp/connect`, `PraisonAIUI /api/mcp/connect`, and `aiui StdioMCPClient`: 0 results.\n- GitHub issue/PR searches in `MervinPraison/PraisonAI` for exact endpoint/function/class terms. Only one unrelated PR was returned for `/api/mcp/connect`; no issue/PR matched `api_mcp_connect`, `StdioMCPClient`, `connect_mcp_server`, or `praisonaiui.features.mcp`.\n- Broad web searches for exact endpoint, file, class, and function terms returned no matching public vulnerability report.\n\nWhy this is distinct from known PraisonAI advisories:\n\n- Not the excluded `praisonai serve agents --api-key` `/agents` auth bypass. This report targets `POST /api/mcp/connect` in the PraisonAIUI host app.\n- Not GHSA-9gm9-c8mq-vq7m / CVE-2026-34935 or GHSA-9qhq-v63v-fv3j / CVE-2026-41497. Those involve `MCPHandler.parse_mcp_command()` command parsing. This finding uses `praisonaiui.server.api_mcp_connect -\u003e praisonaiui.features.mcp.connect_mcp_server -\u003e StdioMCPClient`.\n- Not GHSA-pj2r-f9mw-vrcq / CVE-2026-40159. That advisory concerns sensitive environment variables inherited by untrusted MCP subprocesses. This finding is unauthenticated network-triggered local process execution.\n- Not GHSA-6rmh-7xcm-cpxj or GHSA-8444-4fhq-fxpq. Those concern unauthenticated legacy/generated agent servers. This is a distinct UI route and a distinct sink that starts arbitrary local processes.\n- Not GHSA-9cr9-25q5-8prj, GHSA-9mqq-jqxf-grvw, or other MCP server file-read/path-traversal advisories. This path is the UI MCP client connector, not PraisonAI\u0027s MCP server tool dispatcher.\n\n## Recommended Fix\n\n1. Remove arbitrary `command`/`args` from the remote HTTP API. MCP stdio servers should be configured only from trusted local configuration, not caller-supplied JSON.\n2. Require authentication and authorization on `/api/mcp/connect`, `/api/mcp/disconnect/*`, and `/api/mcp/servers` regardless of `AUTH_ENFORCE`.\n3. Change UI command defaults from `0.0.0.0` to `127.0.0.1`, or require an explicit `--unsafe-expose` style flag when binding externally without auth.\n4. If remote MCP registration is a required feature, allow only URL-based transports with SSRF protections, or maintain an administrator-configured allowlist of commands.\n5. Add regression tests that unauthenticated requests to `/api/mcp/connect` cannot start a subprocess, including when `AUTH_ENFORCE` is unset.",
  "id": "GHSA-p75f-6fp4-p57w",
  "modified": "2026-07-20T21:25:16Z",
  "published": "2026-06-18T13:58:14Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-p75f-6fp4-p57w"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/MervinPraison/PraisonAI"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "PraisonAI: Missing Authentication for Critical Function and Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027) in praisonai"
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.


Detection rules are retrieved from Rulezet.


Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.