Webex Automation

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct users to connect to a remote MCP server at https://rube.app/mcp during setup to provide the necessary tool functionality.\n- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes information from external Webex messages and room memberships which are untrusted sources.\n
  • Ingestion points: Data from external Webex rooms and message content is ingested via tools like WEBEX_MESSAGING_LIST_ROOMS and WEBEX_MESSAGING_LIST_MEMBERSHIPS.\n
  • Boundary markers: No specific delimiters or safety instructions are defined to separate ingested message content from the agent's command logic.\n
  • Capability inventory: The skill has broad capabilities including sending messages, adding team members, and creating webhooks.\n
  • Sanitization: The instructions do not document any specific sanitization or validation processes for data retrieved from Webex.\n- [COMMAND_EXECUTION]: The skill includes a tool for creating webhooks (WEBEX_WEBHOOKS_CREATE_WEBHOOK) that allows the agent to send automated notifications to a user-specified targetUrl.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:11 AM