docusign-automation
Warn
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADS
Full Analysis
- EXTERNAL_DOWNLOADS (MEDIUM): The skill instructions direct the user to add an external URL as an MCP server endpoint.
- Evidence: Found in the 'Setup' section: "Add
https://rube.app/mcpas an MCP server in your client configuration." - Risk:
rube.appis not on the list of trusted organizations or repositories. Connecting an agent to an untrusted MCP server allows that endpoint to define tool schemas and potentially observe or manipulate tool execution data. - INDIRECT_PROMPT_INJECTION (LOW): The skill processes external data from DocuSign templates and envelopes which acts as a potential injection surface.
- Ingestion points:
DOCUSIGN_LIST_ALL_TEMPLATES,DOCUSIGN_GET_TEMPLATE, andDOCUSIGN_GET_ENVELOPEingest data from an external provider (DocuSign). - Boundary markers: Absent. The instructions do not specify using delimiters or ignore-instructions for the data returned from these tools.
- Capability inventory: The skill is restricted to DocuSign API actions (list, get, create, send) and does not include file system access or arbitrary command execution.
- Sanitization: Absent. There is no mention of validating or escaping template names or role strings before they are processed by the agent.
Audit Metadata