mcp-builder
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to fetch protocol specifications and SDK README files from
modelcontextprotocol.ioand themodelcontextprotocolGitHub organization. These are recognized as trusted and well-known services associated with the described technology.- [PROMPT_INJECTION]: The content was scanned for instructions designed to bypass safety filters or override agent behavior. No such patterns, including 'ignore previous instructions' or restricted role-play scenarios, were found.- [COMMAND_EXECUTION]: The skill includes instructions for the user to run standard development commands such asnpm run buildandnpx @modelcontextprotocol/inspectorto verify and test their implementation. These commands are appropriate for the developer-centric context of the skill.
Audit Metadata