freshdesk-automation

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses Freshdesk toolkit calls (e.g., FRESHDESK_VIEW_TICKET / FRESHDESK_LIST_ALL_TICKET_CONVERSATIONS) that will ingest customer-authored ticket/reply/note body text into the agent’s LLM context at runtime, which is outsider free text and can contain prompt-injection payloads.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires adding https://rube.app/mcp as the MCP server and to call RUBE_SEARCH_TOOLS to fetch current tool schemas at runtime, so content served from that URL can directly control the agent's tools/prompts and is a required runtime dependency.