recallai-automation

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches tool configurations and execution schemas from the Composio Rube MCP endpoint at https://rube.app/mcp.
  • [COMMAND_EXECUTION]: Provides tools such as RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH to execute remote functions and workflows based on dynamically discovered tool slugs.
  • [PROMPT_INJECTION]: Identifies an indirect prompt injection surface where the agent processes instructions fetched from external sources.
  • Ingestion points: The agent ingests data retrieved from the RUBE_SEARCH_TOOLS endpoint as described in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the fetched data are defined.
  • Capability inventory: The skill has the ability to execute remote tools and workbenches via RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH.
  • Sanitization: No evidence of validation or sanitization of the remotely fetched execution plans or tool schemas is provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:43 AM