fetch-url
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the
@arabold/docs-mcp-serverpackage from the npm registry. This is the official distribution method for the author's tool and is considered a safe vendor resource. - [COMMAND_EXECUTION]: The skill executes the
npxcommand to run the @arabold/docs-mcp-server utility. - [PROMPT_INJECTION]: The skill facilitates web-scraping which is an inherent surface for indirect prompt injection.
- Ingestion points: Content is fetched from arbitrary URLs as defined in the
fetch-urlcommand parameters inSKILL.md. - Boundary markers: No explicit markers are used to delineate the fetched web content from the agent's instructions.
- Capability inventory: The skill uses
npxto execute scraping logic and network requests. - Sanitization: Content is converted to Markdown but does not include additional sanitization to filter potential LLM instructions.
Audit Metadata