freshdesk-automation

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). This skill's required workflows explicitly instruct the agent to fetch and read customer-created ticket content from Freshdesk (e.g., FRESHDESK_VIEW_TICKET and FRESHDESK_LIST_ALL_TICKET_CONVERSATIONS in the "Reply to and Add Notes on Tickets" flow) and to use that content to compose replies, so untrusted user-generated content can directly influence agent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill requires connecting to Rube MCP at https://rube.app/mcp and calling RUBE_SEARCH_TOOLS at runtime to fetch tool schemas that directly determine the agent's available tools and behavior, making this external endpoint a required source that can control agent instructions.