building-mcp-servers
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches protocol specifications and SDK documentation from official sources, including
modelcontextprotocol.ioand themodelcontextprotocolGitHub organization. These are well-known and trusted providers. - [COMMAND_EXECUTION]: The
scripts/evaluation.pyscript executes local MCP server processes via thestdiotransport. This is a primary function for testing servers and is controlled by user-provided command-line arguments. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via its evaluation harness. 1. Ingestion points:
scripts/evaluation.pyreads questions from external XML files (e.g.,scripts/example_evaluation.xml). 2. Boundary markers: The agent is instructed to use specific XML tags (<summary>,<feedback>,<response>) to separate its internal reasoning from the final answer. 3. Capability inventory: The evaluation agent can invoke any tool exposed by the target MCP server, which may include system-level operations. 4. Sanitization: There is no specific validation or filtering applied to the question content extracted from the XML files.
Audit Metadata