docusign-automation
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires connecting to an external MCP server at 'https://rube.app/mcp' to access the required DocuSign tools.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) when processing DocuSign data. 1. Ingestion points: Fetches template names, recipient roles, and envelope statuses via 'DOCUSIGN_LIST_ALL_TEMPLATES' and 'DOCUSIGN_GET_ENVELOPE' (SKILL.md). 2. Boundary markers: Absent; the skill does not specify delimiters or instructions to the agent to ignore potentially malicious commands within the DocuSign response data. 3. Capability inventory: The skill has the ability to send emails and legal documents through 'DOCUSIGN_SEND_ENVELOPE'. 4. Sanitization: Absent; no validation or filtering of external data is performed before it is processed by the agent.
Audit Metadata