Findings & checks · 1 flagged
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · README.md
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
- Decode the base64 string and confirm it is not an instruction directed at the agent.
- Move any legitimate binary or signature data into a dedicated file (
*.sig,SIGNATURES) outside the documentation.
Trace & refs
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
PyAnsys Common MCP
PyAnsys Common MCP provides the infrastructure for building Model Context Protocol (MCP) servers for PyAnsys libraries.
Overview
This package provides the foundation for creating MCP servers that enable AI assistants (like Claude, ChatGPT) to interact with Ansys products through PyAnsys libraries.
Key features:
- Persistent Python sessions: Maintains stateful code execution across multiple AI requests.
- Lifecycle management: Handles startup, cleanup, and errors automatically.
- Extensible architecture: Uses base classes and patterns for product-specific implementations.
- Logging infrastructure: Uses pre-configured logging that does not interfere with the MCP protocol.
Installation
For users
The `ansys.common.mcp` package currently supports Python 3.10 through Python 3.14 on Windows, Mac OS, and Linux.
Install the latest package for use with this command:
pip install ansys-common-mcpAlternatively, install the latest PyAnsys Common MCP GitHub package with this command:
pip install git+https://github.com/ansys/pyansys-common-mcp.gitFor developers
If you are contributing to PyAnsys Common MCP or creating custom servers, install the package in developer mode:
# Clone the repository
git clone https://github.com/ansys/pyansys-common-mcp.git
cd pyansys-common-mcp
# Install in editable mode with development dependencies
pip install -e .[dev]
# Or install documentation dependencies for building documentation
pip install -e .[doc]Quick start
To create an MCP server for your PyAnsys library, follow these three main steps:
- Define your custom context: Extend the
PyAnsysBaseAppContextdataclass to store the product-specific state. - Implement your MCP server: Extend the
PyAnsysBaseMCPbase class with startup and cleanup logic. - Create MCP tools: Define tools that interact with your product.
Real-world example
For a complete, production-ready implementation, see the PyMAPDL-MCP repository.
Resources
For general PyAnsys questions, email [email protected].