similarweb_digitalrank_api-automation

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill directs users to connect to an external MCP server at 'https://rube.app/mcp'. This domain is not in the list of trusted providers, posing a risk of untrusted infrastructure dependency.
  • REMOTE_CODE_EXECUTION (MEDIUM): Usage of 'RUBE_REMOTE_WORKBENCH' involves executing code on a third-party remote environment. While part of the intended functionality, it constitutes remote execution of logic outside the user's direct control.
  • PROMPT_INJECTION (MEDIUM): The skill is susceptible to indirect prompt injection because it processes external data from SimilarWeb without explicit sanitization or boundary markers.
  • Ingestion points: Data returned from SimilarWeb via 'RUBE_MULTI_EXECUTE_TOOL'.
  • Boundary markers: None specified in the instructions.
  • Capability inventory: The skill can execute tools and run code on a remote workbench based on processed data.
  • Sanitization: No sanitization or validation of the API-returned content is mentioned.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:00 PM