mcp-hub
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs standard Python libraries for document processing (python-docx, openpyxl, python-pptx, reportlab, jinja2) from the public PyPI registry.
- [EXTERNAL_DOWNLOADS]: The skill references and executes official MCP servers (@modelcontextprotocol/server-filesystem and @anthropic/mcp-google-drive) using npx. These originate from well-known and trusted organizations.
- [DATA_EXFILTRATION]: The skill is designed to interact with the local filesystem and external services like Google Drive. This file and data access is the primary intended purpose of the skill and is documented transparently.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface (Category 8) because it processes data from external sources (files, databases, and web pages via Puppeteer).
- Ingestion points: Data enters the agent context through the filesystem MCP, Google Drive API, and SQLite database queries.
- Boundary markers: The provided skill definition does not include specific delimiters or 'ignore' instructions for processed data.
- Capability inventory: The skill enables file read/write operations, database querying, and browser automation.
- Sanitization: No explicit sanitization or filtering of external content is described in the skill configuration.
Audit Metadata