DocuSign Automation

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is primarily documentation-based, providing configuration templates and API usage examples for DocuSign workflows. No malicious command execution or unauthorized data exfiltration patterns were detected.
  • [PROMPT_INJECTION]: The skill processes untrusted external data, creating a potential surface for indirect prompt injection.
  • Ingestion points: Data enters the context through user-provided variables such as contract_name, document_type, and recipient details (signer_1_name, signer_1_email) which are interpolated into envelope and template configurations.
  • Boundary markers: The configuration uses standard Handlebars-style interpolation but lacks explicit boundary markers or instructions to the agent to disregard embedded commands within these fields.
  • Capability inventory: The skill utilizes several MCP tools (docusign_envelope, docusign_template, docusign_signing, docusign_webhook) to interact with the DocuSign API, allowing for the execution of document management actions based on processed inputs.
  • Sanitization: There is no evidence of input validation or sanitization logic to filter potentially malicious instructions within the document metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:21 AM