remote-retrieval-automation

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs users to configure an external MCP server endpoint (https://rube.app/mcp) to enable tool discovery and execution capabilities.
  • [COMMAND_EXECUTION]: Provides instructions for the agent to use powerful execution tools, including RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH, to perform automated workflows based on remote retrieval results.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface where instructions embedded in retrieved remote data could attempt to influence the agent's behavior through the provided execution tools.
  • Ingestion points: External data fetched via the 'remote_retrieval' toolkit (SKILL.md).
  • Boundary markers: No explicit delimiters or 'ignore' instructions are provided for processed data.
  • Capability inventory: Includes tool execution (RUBE_MULTI_EXECUTE_TOOL) and a remote workbench (RUBE_REMOTE_WORKBENCH) as described in SKILL.md.
  • Sanitization: No sanitization or validation logic is specified for the retrieved content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:44 AM