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

GHSA-9GM9-C8MQ-VQ7M

Vulnerability from github – Published: 2026-04-01 23:20 – Updated: 2026-04-06 22:53
VLAI
Summary
PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()
Details

Summary

The --mcp CLI argument is passed directly to shlex.split() and forwarded through the call chain to anyio.open_process() with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command execution as the process user.

Details

cli/features/mcp.py:61 (source) -> praisonaiagents/mcp/mcp.py:345 (hop) -> mcp/client/stdio/__init__.py:253 (sink)

# source
parts = shlex.split(command)

# hop
cmd, args, env = self.parse_mcp_command(command, env_vars)
self.server_params = StdioServerParameters(command=cmd, args=arguments)

# sink
process = await anyio.open_process([command, *args])

Fixed in commit 47bff65413beaa3c21bf633c1fae4e684348368c (v4.5.69) by introducing a command allowlist:

ALLOWED_COMMANDS = {"npx", "uvx", "node", "python"}
if cmd not in ALLOWED_COMMANDS:
    raise ValueError(f"Disallowed command: {cmd}")

PoC

# tested on: praisonai==4.5.48
# install: pip install praisonai==4.5.48
# run: praisonai --mcp "bash -c 'id > /tmp/pwned'"
# verify: cat /tmp/pwned
# expected output: uid=1000(...) gid=1000(...) groups=1000(...)

Impact

Any deployment where the --mcp argument is influenced by untrusted input is exposed to full OS command execution as the process user. No authentication is required.

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= 4.5.68"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "praisonai"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "4.5.15"
            },
            {
              "fixed": "4.5.69"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-34935"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-78"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-04-01T23:20:00Z",
    "nvd_published_at": "2026-04-03T23:17:05Z",
    "severity": "CRITICAL"
  },
  "details": "### Summary\n\nThe `--mcp` CLI argument is passed directly to `shlex.split()` and forwarded through the call chain to `anyio.open_process()` with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command execution as the process user.\n\n### Details\n\n`cli/features/mcp.py:61` (source) -\u003e `praisonaiagents/mcp/mcp.py:345` (hop) -\u003e `mcp/client/stdio/__init__.py:253` (sink)\n```python\n# source\nparts = shlex.split(command)\n\n# hop\ncmd, args, env = self.parse_mcp_command(command, env_vars)\nself.server_params = StdioServerParameters(command=cmd, args=arguments)\n\n# sink\nprocess = await anyio.open_process([command, *args])\n\n```\n\nFixed in commit `47bff65413beaa3c21bf633c1fae4e684348368c` (v4.5.69) by introducing a command allowlist:\n```python\nALLOWED_COMMANDS = {\"npx\", \"uvx\", \"node\", \"python\"}\nif cmd not in ALLOWED_COMMANDS:\n    raise ValueError(f\"Disallowed command: {cmd}\")\n```\n\n### PoC\n```python\n# tested on: praisonai==4.5.48\n# install: pip install praisonai==4.5.48\n# run: praisonai --mcp \"bash -c \u0027id \u003e /tmp/pwned\u0027\"\n# verify: cat /tmp/pwned\n# expected output: uid=1000(...) gid=1000(...) groups=1000(...)\n```\n\n### Impact\n\nAny deployment where the `--mcp` argument is influenced by untrusted input is exposed to full OS command execution as the process user. No authentication is required.",
  "id": "GHSA-9gm9-c8mq-vq7m",
  "modified": "2026-04-06T22:53:58Z",
  "published": "2026-04-01T23:20:00Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9gm9-c8mq-vq7m"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-34935"
    },
    {
      "type": "WEB",
      "url": "https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c"
    },
    {
      "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: OS Command Injection in MCPHandler.parse_mcp_command()"
}



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.