webmcp-designer
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily composed of documentation files (doctrine and stack blueprints) that offer architectural guidance for designing agent-accessible tools. It does not contain any executable scripts, binary files, or automated commands that pose a security risk.
- [PROMPT_INJECTION]: Instructions provided to the agent focus on maintaining the integrity of the human-facing product and ensuring tools are descriptive and well-scoped. No attempts to bypass safety filters or override system constraints were detected.
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to the MCP-B documentation server and first-party website (docs.mcp-b.ai) for exact syntax and package details. These references are strictly for documentation and do not involve downloading or executing remote code or packages.
- [COMMAND_EXECUTION]: While the README provides a sample build command for local development of the skill archive, the skill itself does not instruct the agent to execute any system commands or shell scripts during its operation.
Audit Metadata