felt-automation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • External Downloads (LOW): The skill requires users to add https://rube.app/mcp as an MCP server. While this is the intended setup for the Rube toolkit, the domain is not part of the pre-approved trusted organizations list.
  • Indirect Prompt Injection (LOW): The skill's workflow depends on data fetched from the Rube API at runtime, creating a surface for potential injection if the remote source is compromised.
  • Ingestion points: Tool schemas and metadata returned by RUBE_SEARCH_TOOLS.
  • Boundary markers: None explicitly defined in the prompt instructions to separate tool metadata from instructions.
  • Capability inventory: The skill uses RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH which can execute various automation tasks.
  • Sanitization: No sanitization of the remote tool descriptions or schemas is specified in the skill code.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:46 PM