GHSA-HRCW-XC63-G29M

Vulnerability from github – Published: 2026-05-05 18:55 – Updated: 2026-05-05 18:55
VLAI?
Summary
PPTAgent: Arbitrary File Write + Directory Creation via markdown_table_to_image
Details

Summary

The markdown_table_to_image tool accepts a caller-controlled path parameter and passes it directly to get_html_table_image:

# pptagent/mcp_server.py:127-143
def markdown_table_to_image(markdown_table: str, path: str, css: str) -> str:
    """
    Args:
        path (str): The file path where the image will be saved
    """
    html = markdown_to_html(markdown_table)
    get_html_table_image(html, path, css)           # ← no path validation
    return f"Markdown table converted to image and saved to {path}"

# pptagent/utils.py:337-366
def get_html_table_image(html: str, output_path: str, css: str = None):
    parent_dir, base_name = os.path.split(output_path)
    if parent_dir and not os.path.exists(parent_dir):
        os.makedirs(parent_dir)                     # ← creates arbitrary directories
    hti = Html2Image(...)
    hti.screenshot(
        html_str=html,
        css_str=css,
        save_as=base_name,                          # ← writes image to any directory
        size=(1000, 600),
    )

os.makedirs(parent_dir) creates arbitrary directory trees, and Html2Image.screenshot writes the rendered image to parent_dir/base_name. Unlike download_file in the same project, there is no is_relative_to(workspace) guard. This behaviour can be fixed with the same pattern as the above.

Impact

The concrete attack scenarios include

  • SSH key replacement: path = "/home/user/.ssh/authorized_keys" — replaces the authorized_keys file with an image binary (breaks - SSH but could be an image crafted with a specific PNG/JPEG payload).
  • Web shell: path = "/var/www/html/uploads/shell.php" — writes the rendered PNG there; the file has the .php extension but PNG content; combined with Apache Options +MultiViews or file-include vulnerabilities could be dangerous.
  • Directory creation oracle: path = "/root/test/probe.png" — if the directory is created, confirms the target path exists; if it errors, reveals permissions information.
Severity ?
4.6 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:N/I:L/A:L
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "pptagent"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.1.36"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-42078"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-22"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-05-05T18:55:50Z",
    "nvd_published_at": "2026-05-04T17:16:24Z",
    "severity": "MODERATE"
  },
  "details": "### Summary\n\nThe `markdown_table_to_image` tool accepts a caller-controlled path parameter and passes it directly to `get_html_table_image`:\n\n```python\n# pptagent/mcp_server.py:127-143\ndef markdown_table_to_image(markdown_table: str, path: str, css: str) -\u003e str:\n    \"\"\"\n    Args:\n        path (str): The file path where the image will be saved\n    \"\"\"\n    html = markdown_to_html(markdown_table)\n    get_html_table_image(html, path, css)           # \u2190 no path validation\n    return f\"Markdown table converted to image and saved to {path}\"\n\n# pptagent/utils.py:337-366\ndef get_html_table_image(html: str, output_path: str, css: str = None):\n    parent_dir, base_name = os.path.split(output_path)\n    if parent_dir and not os.path.exists(parent_dir):\n        os.makedirs(parent_dir)                     # \u2190 creates arbitrary directories\n    hti = Html2Image(...)\n    hti.screenshot(\n        html_str=html,\n        css_str=css,\n        save_as=base_name,                          # \u2190 writes image to any directory\n        size=(1000, 600),\n    )\n```\n\n`os.makedirs(parent_dir)` creates arbitrary directory trees, and `Html2Image.screenshot` writes the rendered image to `parent_dir/base_name`. Unlike `download_file` in the same project, there is no `is_relative_to(workspace)` guard. This behaviour can be fixed with the same pattern as the above.\n\n\n### Impact\n\nThe concrete attack scenarios include\n\n- SSH key replacement: `path = \"/home/user/.ssh/authorized_keys\"` \u2014 replaces the authorized_keys file with an image binary (breaks - SSH but could be an image crafted with a specific PNG/JPEG payload).\n- Web shell: `path = \"/var/www/html/uploads/shell.php\"` \u2014 writes the rendered PNG there; the file has the .php extension but PNG content; combined with Apache Options +MultiViews or file-include vulnerabilities could be dangerous.\n- Directory creation oracle: `path = \"/root/test/probe.png\"` \u2014 if the directory is created, confirms the target path exists; if it errors, reveals permissions information.",
  "id": "GHSA-hrcw-xc63-g29m",
  "modified": "2026-05-05T18:55:50Z",
  "published": "2026-05-05T18:55:50Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/icip-cas/PPTAgent/security/advisories/GHSA-hrcw-xc63-g29m"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-42078"
    },
    {
      "type": "WEB",
      "url": "https://github.com/icip-cas/PPTAgent/commit/418491a9a1c02d9d93194b5973bb58df35cf9d00"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/icip-cas/PPTAgent"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:N/I:L/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "PPTAgent: Arbitrary File Write + Directory Creation via markdown_table_to_image"
}


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.