anthropic-mcp-builder

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill implements automated testing via scripts/evaluation.py and scripts/connections.py, which utilize the Model Context Protocol library to spawn local subprocesses using user-provided commands and arguments. This functionality is the primary intended purpose of the evaluation harness for server development.
  • [EXTERNAL_DOWNLOADS]: SKILL.md and the reference implementation guides instruct the agent to fetch documentation and schema information from trusted and well-known sources, specifically the official modelcontextprotocol.io website and verified modelcontextprotocol organization repositories on GitHub.
  • [PROMPT_INJECTION]: The evaluation loop in scripts/evaluation.py presents an indirect prompt injection surface by ingesting external data from question files and tool results from connected servers into the agent context. 1. Ingestion points: XML evaluation files and tool outputs within the agent loop in scripts/evaluation.py. 2. Boundary markers: The script relies on the EVALUATION_PROMPT system instructions and standard SDK tool result structures to isolate untrusted content. 3. Capability inventory: The skill facilitates local command execution via stdio and manages network connections via SSE and HTTP transports. 4. Sanitization: The script lacks explicit content filtering or sanitization of data returned by tools before it is interpolated into the AI model's prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 01:48 PM