mcp-server-design
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of a bundled Python script to validate tool definitions. This script operates locally using standard libraries and does not engage in network activity or privileged operations.
- [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it is designed to ingest and analyze external JSON data (e.g., tools.json). Ingestion points: The linting script accepts an external file path as a command-line argument and parses its content. Boundary markers: The skill does not define specific delimiters for separating processed data from instructions. Capability inventory: The skill uses standard file reading and python3 execution capabilities to perform its tasks. Sanitization: The validation script uses JSON schema-like checks and regular expressions to enforce structure and naming conventions.
- [EXTERNAL_DOWNLOADS]: The skill and its references point to official and well-known developer resources, such as the Model Context Protocol documentation and GitHub repositories from trusted organizations. These references are used for informational purposes and do not trigger unauthorized downloads.
Audit Metadata