skills/vm0-ai/vm0-skills/similarweb/Gen Agent Trust Hub

similarweb

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to api.similarweb.com, the official endpoint for Similarweb. As this is a well-known analytics service, the network operations are considered normal and expected functionality.
  • [COMMAND_EXECUTION]: Standard command-line tools curl and jq are used to interact with the Similarweb API and format results. These are used safely within the documented examples.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface typical of data-retrieval tools. Ingestion points: User-provided domains and Similarweb API response data (SKILL.md). Boundary markers: No specific delimiters are used to separate input/output data from the agent's instructions. Capability inventory: Uses curl for API requests. Sanitization: No explicit input validation is performed on the provided domains or API results, which is a common characteristic of such integration tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 04:44 PM