repairshopr-automation

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to add an external MCP server endpoint (https://rube.app/mcp) to their client configuration. This is the primary mechanism for the skill's functionality and is documented as part of the official setup.
  • [COMMAND_EXECUTION]: The skill uses specialized tools such as RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH to interact with the Repairshopr API. These operations are within the scope of the skill's intended purpose for business automation.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface by retrieving "recommended execution plans" and tool schemas from a remote discovery tool.
  • Ingestion points: Data enters the context via the RUBE_SEARCH_TOOLS response in SKILL.md workflows.
  • Boundary markers: No explicit boundary markers or instruction-separation warnings are provided for the discovery data.
  • Capability inventory: The skill has the capability to execute API-driven automation tasks via RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH across all described workflows.
  • Sanitization: There is no mention of sanitization or validation of the schemas and plans retrieved from the remote server.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:45 AM