webmcp-context-provider
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation from the Web Machine Learning GitHub Pages repository (webmachinelearning.github.io) and perform searches on official developer sites.- [INDIRECT_PROMPT_INJECTION]: The skill provides a mechanism for injecting external page context and metadata into the agent.
- Ingestion points: The
metadataproperty within theprovideContextAPI calls described in SKILL.md. - Boundary markers: None explicitly defined in the code examples provided.
- Capability inventory: The skill is configured with access to
Bash,Write,Edit,WebSearch, andWebFetchtools. - Sanitization: The skill includes explicit best practices advising users to avoid including sensitive personal information like emails or addresses in the metadata context.
Audit Metadata