u301-automation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [External Downloads] (LOW): The skill requires the user to configure an external MCP server endpoint at https://rube.app/mcp. This domain is not on the predefined trusted list, representing an unverifiable remote dependency. However, this is the intended primary purpose of the skill.
  • [Indirect Prompt Injection] (LOW): The skill exhibits an indirect prompt injection surface by design, as it instructs the agent to fetch and follow execution plans and schemas from a remote source at runtime.
  • Ingestion points: Untrusted data enters the agent context through the results of the RUBE_SEARCH_TOOLS command (specifically tool slugs, schemas, and execution plans).
  • Boundary markers: Absent; there are no instructions provided to the agent to treat the remote schema data as untrusted or to ignore embedded instructions.
  • Capability inventory: The skill provides access to powerful tools like RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH, which can execute arbitrary logic based on the fetched schemas.
  • Sanitization: No sanitization or validation of the remote content is mentioned or implemented in the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:36 PM