mcp-builder

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill implements utilities to execute local commands for the purpose of launching and interacting with MCP servers during development and testing.
  • Evidence: scripts/connections.py and scripts/evaluation.py utilize the mcp.client.stdio transport to manage server subprocesses.
  • [INDIRECT_PROMPT_INJECTION]: The automated evaluation harness ingest results from external tools, creating a vulnerability surface where a malicious tool output could attempt to override the evaluating agent's instructions.
  • Ingestion points: scripts/evaluation.py reads tool results in the agent_loop function and injects them into the message history.
  • Boundary markers: The EVALUATION_PROMPT requires the agent to wrap its output in specific XML tags (<summary>, <feedback>, <response>), providing a structural defense against output hijacking.
  • Capability inventory: The skill can execute shell commands via the mcp SDK and perform network operations via the Anthropic API.
  • Sanitization: Tool outputs are stringified and included in the prompt context without content-based filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 08:40 AM