venly-automation

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires connecting to an external Model Context Protocol (MCP) server at https://rube.app/mcp. This server provides tool definitions and the execution environment for Venly operations.
  • [COMMAND_EXECUTION]: The skill invokes tools such as RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH to perform operations on the remote platform.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface. It dynamically retrieves tool schemas and execution strategies from the remote server using the RUBE_SEARCH_TOOLS command. These instructions are then used to guide subsequent agent actions. * Ingestion points: Data retrieved from the RUBE_SEARCH_TOOLS call in SKILL.md. * Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present. * Capability inventory: The skill can execute various automation tasks through the RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH capabilities. * Sanitization: There is no indicated sanitization of the externally retrieved tool definitions or execution plans.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:08 AM