GHSA-2RCG-MM5H-XCHX

Vulnerability from github – Published: 2026-06-18 13:57 – Updated: 2026-07-20 21:26
VLAI
Summary
PraisonAI: Arbitrary File Read via `@file:` Mention Path Traversal
Details

Summary

The MentionsParser in src/praisonai-agents/praisonaiagents/tools/mentions.py processes @file: mentions in agent prompts by reading arbitrary files from the filesystem. When a file path is not found relative to the workspace, the parser falls back to using the path as an absolute path without any validation or boundary check. This allows an attacker who can influence agent prompts (via chat messages, Telegram/Discord/Slack bot inputs, or YAML workflow configs) to read any file on the filesystem accessible to the process user.

Details

Vulnerable code (lines 165–178):

def _process_file_mention(self, file_path: str) -> Optional[str]:
    """Process @file:path mention."""
    try:
        # Resolve path relative to workspace
        full_path = self.workspace_path / file_path
        if not full_path.exists():
            # Try as absolute path
            full_path = Path(file_path)

        if not full_path.exists():
            self._log(f"File not found: {file_path}", logging.WARNING)
            return f"# File: {file_path}\n[File not found]"

        content = full_path.read_text(encoding="utf-8")

The vulnerability is in the fallback at line 171–172: When the file is not found relative to workspace_path, the code constructs full_path = Path(file_path), which accepts any absolute or relative path without validation. There is no: - .. path traversal check - Workspace boundary validation - Symlink resolution against workspace - Protected path guard

The file_path parameter originates from parsing @file: mentions in user/LLM prompts. The MentionsParser is used across the framework to process mentions in agent instructions and user messages.

Contrast with skill_tools.py read_skill_file (lines 140–193), which properly validates:

# skill_tools.py line 179 — proper validation
if os.path.commonpath([full_path, skill_path]) != skill_path:
    return f"Error: Path traversal detected - {file_path} is outside skill directory"

PoC

Setup: Clean checkout at commit d5f1114a.

Positive trigger — arbitrary file read via @file: mention:

import sys
sys.path.insert(0, 'src/praisonai-agents')
from praisonaiagents.tools.mentions import MentionsParser

parser = MentionsParser()

# Test 1: Absolute path read (bypasses workspace resolution)
result = parser._process_file_mention('/etc/hostname')
print(f'Absolute path read: {result[:80]}...')

# Test 2: Relative path with traversal
result = parser._process_file_mention('../../../etc/hostname')
print(f'Traversal read: {result[:80]}...')

Expected output:

Absolute path read: # File: /etc/hostname
```linux
<hostname>
```...
Traversal read: # File: ../../../etc/hostname
```linux
<hostname>
```...

Negative control — non-existent file:

result = parser._process_file_mention('/nonexistent/secret.txt')
# Returns: "# File: /nonexistent/secret.txt\n[File not found]"

Cleanup: No persistence or side effects — read-only operation.

Impact

An attacker who can inject @file: mentions into agent prompts (via chat messages in Telegram/Discord/Slack bots, user input in web UI, or YAML workflow configurations) can read any file accessible to the process user, including:

  • Secrets and credentials: .env files, ~/.aws/credentials, ~/.ssh/id_rsa, API keys
  • Configuration files: Database passwords, JWT secrets, OAuth tokens
  • Source code: Application internals, database schemas
  • System files: /etc/passwd, /etc/shadow (if process has read access)

This is particularly dangerous in bot deployments where auto_approve_tools defaults to True and untrusted users can send messages containing @file: mentions.

Suggested remediation

  1. Remove the absolute path fallback. Only resolve files within workspace_path:
def _process_file_mention(self, file_path: str) -> Optional[str]:
    full_path = (self.workspace_path / file_path).resolve()
    # Ensure resolved path is within workspace
    if not str(full_path).startswith(str(self.workspace_path.resolve())):
        return f"# File: {file_path}\n[Access denied: path outside workspace]"
    if not full_path.exists():
        return f"# File: {file_path}\n[File not found]"
    content = full_path.read_text(encoding="utf-8")

  1. Add symlink resolution via .resolve() to prevent symlink-based traversal.

  2. Add a protected path guard (.env, .git, .ssh, keys, credentials).

  3. Apply the same os.path.commonpath pattern used by skill_tools.py.

Credits

  • Thai Son Dinh from VinSOC Labs (R&D)
Severity
7.5 (High)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 1.6.48"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "praisonaiagents"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.6.59"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-57129"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-22"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-06-18T13:57:00Z",
    "nvd_published_at": null,
    "severity": "HIGH"
  },
  "details": "## Summary\n\nThe MentionsParser in `src/praisonai-agents/praisonaiagents/tools/mentions.py` processes `@file:` mentions in agent prompts by reading arbitrary files from the filesystem. When a file path is not found relative to the workspace, the parser falls back to using the path as an absolute path without any validation or boundary check. This allows an attacker who can influence agent prompts (via chat messages, Telegram/Discord/Slack bot inputs, or YAML workflow configs) to read any file on the filesystem accessible to the process user.\n\n## Details\n**Vulnerable code (lines 165\u2013178):**\n```python\ndef _process_file_mention(self, file_path: str) -\u003e Optional[str]:\n    \"\"\"Process @file:path mention.\"\"\"\n    try:\n        # Resolve path relative to workspace\n        full_path = self.workspace_path / file_path\n        if not full_path.exists():\n            # Try as absolute path\n            full_path = Path(file_path)\n        \n        if not full_path.exists():\n            self._log(f\"File not found: {file_path}\", logging.WARNING)\n            return f\"# File: {file_path}\\n[File not found]\"\n        \n        content = full_path.read_text(encoding=\"utf-8\")\n```\n\n**The vulnerability is in the fallback at line 171\u2013172:** When the file is not found relative to `workspace_path`, the code constructs `full_path = Path(file_path)`, which accepts any absolute or relative path without validation. There is no:\n- `..` path traversal check\n- Workspace boundary validation\n- Symlink resolution against workspace\n- Protected path guard\n\nThe `file_path` parameter originates from parsing `@file:` mentions in user/LLM prompts. The `MentionsParser` is used across the framework to process mentions in agent instructions and user messages.\n\n**Contrast with `skill_tools.py` `read_skill_file`** (lines 140\u2013193), which properly validates:\n```python\n# skill_tools.py line 179 \u2014 proper validation\nif os.path.commonpath([full_path, skill_path]) != skill_path:\n    return f\"Error: Path traversal detected - {file_path} is outside skill directory\"\n```\n\n## PoC\n\n**Setup:** Clean checkout at commit `d5f1114a`.\n\n**Positive trigger \u2014 arbitrary file read via @file: mention:**\n```python\nimport sys\nsys.path.insert(0, \u0027src/praisonai-agents\u0027)\nfrom praisonaiagents.tools.mentions import MentionsParser\n\nparser = MentionsParser()\n\n# Test 1: Absolute path read (bypasses workspace resolution)\nresult = parser._process_file_mention(\u0027/etc/hostname\u0027)\nprint(f\u0027Absolute path read: {result[:80]}...\u0027)\n\n# Test 2: Relative path with traversal\nresult = parser._process_file_mention(\u0027../../../etc/hostname\u0027)\nprint(f\u0027Traversal read: {result[:80]}...\u0027)\n```\n\n**Expected output:**\n```\nAbsolute path read: # File: /etc/hostname\n```linux\n\u003chostname\u003e\n```...\nTraversal read: # File: ../../../etc/hostname\n```linux\n\u003chostname\u003e\n```...\n```\n\n**Negative control \u2014 non-existent file:**\n```python\nresult = parser._process_file_mention(\u0027/nonexistent/secret.txt\u0027)\n# Returns: \"# File: /nonexistent/secret.txt\\n[File not found]\"\n```\n\n**Cleanup:** No persistence or side effects \u2014 read-only operation.\n\n## Impact\n\nAn attacker who can inject `@file:` mentions into agent prompts (via chat messages in Telegram/Discord/Slack bots, user input in web UI, or YAML workflow configurations) can read any file accessible to the process user, including:\n\n- **Secrets and credentials:** `.env` files, `~/.aws/credentials`, `~/.ssh/id_rsa`, API keys\n- **Configuration files:** Database passwords, JWT secrets, OAuth tokens\n- **Source code:** Application internals, database schemas\n- **System files:** `/etc/passwd`, `/etc/shadow` (if process has read access)\n\nThis is particularly dangerous in bot deployments where `auto_approve_tools` defaults to `True` and untrusted users can send messages containing `@file:` mentions.\n\n## Suggested remediation\n\n1. **Remove the absolute path fallback.** Only resolve files within `workspace_path`:\n```python\ndef _process_file_mention(self, file_path: str) -\u003e Optional[str]:\n    full_path = (self.workspace_path / file_path).resolve()\n    # Ensure resolved path is within workspace\n    if not str(full_path).startswith(str(self.workspace_path.resolve())):\n        return f\"# File: {file_path}\\n[Access denied: path outside workspace]\"\n    if not full_path.exists():\n        return f\"# File: {file_path}\\n[File not found]\"\n    content = full_path.read_text(encoding=\"utf-8\")\n```\n\n2. Add symlink resolution via `.resolve()` to prevent symlink-based traversal.\n\n3. Add a protected path guard (`.env`, `.git`, `.ssh`, keys, credentials).\n\n4. Apply the same `os.path.commonpath` pattern used by `skill_tools.py`.\n\n### Credits\n- Thai Son Dinh from VinSOC Labs (R\u0026D)",
  "id": "GHSA-2rcg-mm5h-xchx",
  "modified": "2026-07-20T21:26:29Z",
  "published": "2026-06-18T13:57:00Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2rcg-mm5h-xchx"
    },
    {
      "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:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "PraisonAI: Arbitrary File Read via `@file:` Mention Path Traversal"
}



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.