resend-automation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill configuration requires the addition of an external MCP server (https://rube.app/mcp). While this is the operational endpoint for the service, the domain is not included in the pre-approved trusted sources list, constituting an untrusted external dependency.
  • [Indirect Prompt Injection] (LOW): The core workflow relies on dynamic tool discovery which introduces a surface for malicious instructions to be ingested from the remote server. ● Ingestion points: Tool schemas and descriptions returned by RUBE_SEARCH_TOOLS. ● Boundary markers: Absent; there are no instructions provided to the agent to treat fetched metadata as untrusted or to ignore embedded instructions. ● Capability inventory: The skill has the ability to execute remote operations and bulk tasks via RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH. ● Sanitization: Absent; the skill instructs the agent to use the exact field names and types provided by the remote discovery service without validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:45 PM