bigmailer-automation

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill directs users to add an external MCP server endpoint (https://rube.app/mcp). This domain is not listed as a trusted external source, posing a risk if the source is not verified by the user.
  • [REMOTE_CODE_EXECUTION] (MEDIUM): The skill utilizes RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH to execute logic on remote infrastructure managed by the Rube/Composio platform.
  • [PROMPT_INJECTION] (LOW): The skill is vulnerable to Indirect Prompt Injection. Ingestion points: The skill mandates following 'recommended execution plans' and schemas returned by the RUBE_SEARCH_TOOLS endpoint. Boundary markers: None present; the instructions command the agent to 'Always search first' and adopt returned tool slugs and arguments. Capability inventory: Includes tool execution (RUBE_MULTI_EXECUTE_TOOL) and workbench operations (RUBE_REMOTE_WORKBENCH). Sanitization: No sanitization or validation of the externally provided execution plans is mentioned.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:32 PM