webmcp-mcp-bridge
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill encourages fetching documentation from external sources like the Web Machine Learning GitHub IO page and search engine results to inform bridge implementation. This untrusted data is ingested into the agent context.
- Ingestion points: Documentation fetches from webmachinelearning.github.io and WebSearch results in the 'Before writing code' section.
- Boundary markers: None present in the provided instructions.
- Capability inventory: Includes Bash, Write, Edit, and Read tools.
- Sanitization: None present.
- [EXTERNAL_DOWNLOADS]: Fetches protocol specifications from the official Web Machine Learning GitHub documentation site to provide implementation context.
Audit Metadata