CVE-2026-34935: PraisonAI OS Command Injection Vulnerability

CRITICAL
Advisory Identifier: GHSA-9gm9-c8mq-vq7m
Share
CVSS 9.8
CWE-78
Published
Advisory Summary

CVE-2026-34935 is a CRITICAL (CVSS 9.8) os command injection vulnerability (CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')) affecting PraisonAI libraries in the PyPI ecosystem. The issue involves os command injection in mcphandler.parse_mcp_command(). Remediation is available by upgrading affected packages to version 4.5.69.

CVE-2026-34935 at a Glance

CVE Identifier CVE-2026-34935
GHSA Identifier GHSA-9gm9-c8mq-vq7m
Severity CRITICAL
CVSS v3.1 Base Score 9.8
CWE Classification CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
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-2026-34935

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: 4.5.69 
pip install praisonai>=4.5.69
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-2026-34935, 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 4.5.69), 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-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection'), where the product constructs all or part of an os command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended os command when it is sent to a downstream component. 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 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) ```python # 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: ```python ALLOWED_COMMANDS = {"npx", "uvx", "node", "python"} if cmd not in ALLOWED_COMMANDS: raise ValueError(f"Disallowed command: {cmd}") ``` ### PoC ```python # 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.

CVE-2026-34935 Affected PraisonAI Versions

1 component(s)
Fixed Versions:
4.5.69
Product / Package Ecosystem Affected Versions Fixed Version
praisonai
pypi/praisonai
PyPI
≥ 4.5.15
< 4.5.69
4.5.69

References

GitHub Advisory / Wiki ADVISORY
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9gm9-c8mq-vq7m
NVD — CVE-2026-34935 NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-34935
Security Fix Commit FIX COMMIT
https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c
PraisonAI Source Repository REPOSITORY
https://github.com/MervinPraison/PraisonAI

Frequently Asked Questions

What is CVE-2026-34935?
CVE-2026-34935 is a security vulnerability in PraisonAI involving OS Command Injection in MCPHandler.parse_mcp_command() under CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection').
Which PraisonAI versions are affected?
Affected versions include releases prior to 4.5.69 across affected packages: praisonai.
What version fixes CVE-2026-34935?
Upgrading to 4.5.69 (or the latest patched release for your respective branch) resolves the vulnerability.
Is praisonai affected?
Yes, praisonai is affected in releases prior to 4.5.69. Upgrade your dependency to 4.5.69 or later.
What is the CVSS score of CVE-2026-34935?
CVE-2026-34935 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-2026-34935?
CVE-2026-34935 is classified under CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') (The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.).
How can I check PyPI dependencies for CVE-2026-34935?
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
View Raw JSON 
{
  "schema_version" : "1.4.0",
  "id" : "GHSA-9gm9-c8mq-vq7m",
  "modified" : "2026-04-06T22:53:58Z",
  "published" : "2026-04-01T23:20:00Z",
  "aliases" : [ "CVE-2026-34935" ],
  "summary" : "PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()",
  "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) -> `praisonaiagents/mcp/mcp.py:345` (hop) -> `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 'id > /tmp/pwned'\"\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.",
  "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" : "4.5.15"
      }, {
        "fixed" : "4.5.69"
      } ]
    } ],
    "database_specific" : {
      "last_known_affected_version_range" : "<= 4.5.68"
    }
  } ],
  "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"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-78" ],
    "severity" : "CRITICAL",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-04-01T23:20:00Z",
    "nvd_published_at" : "2026-04-03T23:17:05Z"
  }
}