claude-code-mcp-setup
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and does not contain any executable code, scripts, or malicious prompt injection patterns.
- [SAFE]: External references and package dependencies target the official Model Context Protocol organization, which is a recognized and trusted source for this ecosystem.
- [INDIRECT_PROMPT_INJECTION]: The skill documents the configuration of remote MCP servers and local commands. This defines the data ingestion and execution surface for the tool. As this is the intended purpose of the documented protocol and the skill contains no malicious payloads or instructions to connect to untrusted sources, it is documented as a standard operational feature.
Audit Metadata