GHSA-G985-WJH9-QXXC

Vulnerability from github – Published: 2026-04-10 19:32 – Updated: 2026-04-14 21:54
VLAI?
Summary
PraisonAI Vulnerable to RCE via Automatic tools.py Import
Details

PraisonAI automatically imports ./tools.py from the current working directory when launching certain components. This includes call.py, tool_resolver.py, and CLI tool-loading paths.

A malicious tools.py placed in the process working directory is executed immediately, allowing arbitrary Python code execution in the host environment.

Affected Code

  • call.py → import_tools_from_file()
  • tool_resolver.py → _load_local_tools()
  • tools.py → local tool import flow

PoC

Create tools.py in the directory where PraisonAI is launched:

# tools.py
import os
os.system("echo pwned > /tmp/pwned.txt")

Run any PraisonAI component that loads local tools, for example:

praisonai workflow run safe.yaml

Reproduction Steps

  1. Create a malicious tools.py in the current working directory.
  2. Start PraisonAI or invoke a CLI command that loads local tools.
  3. Verify that /tmp/pwned.txt or the malicious command output exists.

Impact

An attacker who can place or influence tools.py in the working directory can execute arbitrary code in the PraisonAI process, compromising the host and any connected data.

Reporter: Lakshmikanthan K (letchupkt)

Severity ?
8.4 (High)
CVSS:3.1/AV:L/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= 1.5.139"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "praisonaiagents"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.5.140"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 4.5.138"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "PraisonAI"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "4.5.139"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-40287"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-426",
      "CWE-94"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-04-10T19:32:32Z",
    "nvd_published_at": "2026-04-14T04:17:11Z",
    "severity": "HIGH"
  },
  "details": "PraisonAI automatically imports `./tools.py` from the current working directory when launching certain components. This includes call.py, tool_resolver.py, and CLI tool-loading paths.\n\nA malicious tools.py placed in the process working directory is executed immediately, allowing arbitrary Python code execution in the host environment.\n\n### Affected Code\n- call.py \u2192 `import_tools_from_file()`\n- tool_resolver.py \u2192 `_load_local_tools()`\n- tools.py \u2192 local tool import flow\n- \n\n### PoC\nCreate tools.py in the directory where PraisonAI is launched:\n\n```python\n# tools.py\nimport os\nos.system(\"echo pwned \u003e /tmp/pwned.txt\")\n```\n\nRun any PraisonAI component that loads local tools, for example:\n\n```bash\npraisonai workflow run safe.yaml\n```\n\n### Reproduction Steps\n1. Create a malicious tools.py in the current working directory.\n2. Start PraisonAI or invoke a CLI command that loads local tools.\n3. Verify that `/tmp/pwned.txt` or the malicious command output exists.\n\n### Impact\nAn attacker who can place or influence tools.py in the working directory can execute arbitrary code in the PraisonAI process, compromising the host and any connected data.\n\n**Reporter:** Lakshmikanthan K (letchupkt)",
  "id": "GHSA-g985-wjh9-qxxc",
  "modified": "2026-04-14T21:54:23Z",
  "published": "2026-04-10T19:32:32Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-g985-wjh9-qxxc"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-40287"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/MervinPraison/PraisonAI"
    },
    {
      "type": "WEB",
      "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.5.139"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "PraisonAI Vulnerable to RCE via Automatic tools.py Import"
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

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.