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-server package 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 npx command 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-url command parameters in SKILL.md.
  • Boundary markers: No explicit markers are used to delineate the fetched web content from the agent's instructions.
  • Capability inventory: The skill uses npx to 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
Risk Level
SAFE
Analyzed
Mar 17, 2026, 08:31 PM