webmcp-tool-schemas
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the WebMCP inputSchema specification from the project's official documentation site at
https://webmachinelearning.github.io/webmcp/to guide the design process. - [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation and web search results to refine tool schemas.
- Ingestion points: Documentation URLs and web search result content mentioned in SKILL.md.
- Boundary markers: Not explicitly defined for external content ingestion.
- Capability inventory: Access to Bash, Write, and WebFetch tools as defined in the frontmatter.
- Sanitization: Not applicable as the skill uses external data solely for informational design reference.
Audit Metadata