webmcp-engineering
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists of documentation and best practice guides for developers. It does not include any executable scripts, tools, or automated commands that perform actions on the user's system or network.
- [NO_CODE]: The skill does not bundle any scripts, binaries, or executable logic; all files are informational markdown or metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill specifically addresses indirect prompt injection by advising developers to use risk hints, such as
untrustedContentHint, to prevent agents from interpreting data as instructions. - [EXTERNAL_DOWNLOADS]: The documentation mentions optional libraries for WebMCP implementation, including
@mcp-b/webmcp-polyfilland@mcp-b/global. These are informational references to established framework dependencies.
Audit Metadata