mcp-builder

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions and documentation references fetch content from official and well-known sources, including the Model Context Protocol website (modelcontextprotocol.io) and its official GitHub repository. These fetches are for protocol specifications, README documentation, and SDK guidelines, which are necessary for the skill's primary function.
  • [COMMAND_EXECUTION]: The evaluation harness provided in scripts/evaluation.py and scripts/connections.py allows for the execution of local MCP servers via a subprocess when using the stdio transport. This is the standard operational model for testing MCP servers and is performed locally under the developer's control.
  • [INDIRECT_PROMPT_INJECTION]: The scripts/evaluation.py tool possesses an indirect prompt injection attack surface as it processes external data.
  • Ingestion points: The script reads evaluation tasks (questions and ground truth answers) from an XML file provided by the user via the CLI.
  • Boundary markers: The EVALUATION_PROMPT system prompt establishes clear structural boundaries using XML tags (<summary>, <feedback>, <response>) to separate instructions from the data being processed.
  • Capability inventory: The script can list and call tools on the target MCP server using the official mcp client library.
  • Sanitization: Output processing uses regular expressions to extract content from tags, ensuring logical separation between the AI's reasoning and the final response.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:22 PM