mal-2025-191926
Vulnerability from ossf_malicious_packages
Published
2025-11-05 21:25
Modified
2025-12-31 02:45
Summary
Malicious code in wayspiritmcp-tpa (PyPI)
Details

-= Per source details. Do not edit below this line.=-

Source: kam193 (523cbbda7a0fda2addfcd432b1bfcc1df072ee67a593ffce535b7da7005caae8)

Package seems to provide an MCP server, but in fact contains attempts to make an LLM agent break safeguards. As the request is about leaves just a flag, it seems to be research.

Category: PROBABLY_PENTEST - Packages looking like typical pentest packages, but also anything that looks like testing, exploring pre-prepared kits, research & co, with clearly low-harm possibilities.

Campaign: 2025-11-wayspirit

Reasons (based on the campaign):

  • llm-threat
Credits
Kamil Mańkowski (kam193) github.com/kam193 bad-packages.kam193.eu/
Kamil Mańkowski (kam193) github.com/kam193 bad-packages.kam193.eu/
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "wayspiritmcp-tpa"
      },
      "versions": [
        "0.1.3",
        "0.1.2",
        "0.1.1",
        "0.1.0"
      ]
    }
  ],
  "credits": [
    {
      "contact": [
        "https://github.com/kam193",
        "https://bad-packages.kam193.eu/"
      ],
      "name": "Kamil Ma\u0144kowski (kam193)"
    },
    {
      "contact": [
        "https://github.com/kam193",
        "https://bad-packages.kam193.eu/"
      ],
      "name": "Kamil Ma\u0144kowski (kam193)",
      "type": "REPORTER"
    }
  ],
  "database_specific": {
    "malicious-packages-origins": [
      {
        "id": "pypi/2025-11-wayspirit/wayspiritmcp-tpa",
        "import_time": "2025-12-02T22:30:56.503131981Z",
        "modified_time": "2025-11-05T21:25:33.391547Z",
        "sha256": "cf7266476ff9da6367d49cc38fb80547ca59df4a1cc82533d39e147c59f32b7e",
        "source": "kam193",
        "versions": [
          "0.1.3",
          "0.1.2",
          "0.1.1",
          "0.1.0"
        ]
      },
      {
        "id": "pypi/2025-11-wayspirit/wayspiritmcp-tpa",
        "import_time": "2025-12-02T23:07:19.686981651Z",
        "modified_time": "2025-11-05T21:25:33.391547Z",
        "sha256": "523cbbda7a0fda2addfcd432b1bfcc1df072ee67a593ffce535b7da7005caae8",
        "source": "kam193",
        "versions": [
          "0.1.3",
          "0.1.2",
          "0.1.1",
          "0.1.0"
        ]
      },
      {
        "id": "pypi/2025-11-wayspirit/wayspiritmcp-tpa",
        "import_time": "2025-12-30T22:39:04.368236136Z",
        "modified_time": "2025-11-05T21:25:33.391547Z",
        "sha256": "4029a79f3ddeba0f6a5613815b682e027dc2f3d7c66c47bb8fc23ab4de315c8f",
        "source": "kam193",
        "versions": [
          "0.1.0",
          "0.1.1",
          "0.1.2",
          "0.1.3"
        ]
      }
    ]
  },
  "details": "\n---\n_-= Per source details. Do not edit below this line.=-_\n\n## Source: kam193 (523cbbda7a0fda2addfcd432b1bfcc1df072ee67a593ffce535b7da7005caae8)\nPackage seems to provide an MCP server, but in fact contains attempts to make an LLM agent break safeguards. As the request is about leaves just a flag, it seems to be research.\n\n\n---\n\nCategory: PROBABLY_PENTEST - Packages looking like typical pentest packages, but also anything that looks like testing, exploring pre-prepared kits, research \u0026 co, with clearly low-harm possibilities.\n\n\nCampaign: 2025-11-wayspirit\n\n\nReasons (based on the campaign):\n\n\n - llm-threat\n",
  "id": "MAL-2025-191926",
  "modified": "2025-12-31T02:45:16Z",
  "published": "2025-11-05T21:25:33Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://bad-packages.kam193.eu/pypi/package/wayspiritmcp-tpa"
    }
  ],
  "schema_version": "1.7.4",
  "summary": "Malicious code in wayspiritmcp-tpa (PyPI)"
}


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.