docusign-automation

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

• Third-party content exposure detected (low risk: 0.10). The required workflow only ingests text from DocuSign tool responses (e.g., via DOCUSIGN_LIST_ALL_TEMPLATES, DOCUSIGN_GET_TEMPLATE, DOCUSIGN_GET_ENVELOPE) and does not describe any runtime reading of outsider-authored free text without selecting specific items.

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 and connecting to https://rube.app/mcp as the Rube MCP server and instructs calling RUBE_SEARCH_TOOLS to fetch current tool schemas at runtime, so content from that URL will be fetched and can directly control available tools/agent behavior.