Skills
Navigate
skills/cdatasoftware/connect-ai-skills/connect-ai-docusign/Gen Agent Trust Hub

connect-ai-docusign

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill documents access to DocuSign data fields such as EmailSubject, DocumentName, and Name (Recipients), which are controlled by external parties and could contain malicious instructions designed to manipulate agent behavior.
  • Ingestion points: Envelopes, Documents, and Recipients tables in SKILL.md.
  • Boundary markers: No delimiters or protective instructions are specified for handling these fields.
  • Capability inventory: The skill identifies procedures for creating and sending envelopes (CreateAndSendEnvelope) and downloading documents (DownloadDocument).
  • Sanitization: There is no mention of sanitizing or validating the content retrieved from DocuSign.
  • [DATA_EXFILTRATION]: The skill describes the @DocumentsAggregate parameter for the CreateAndSendEnvelope and CreateTemplate procedures, which includes a remoteUrl field. This feature enables the connector to perform network requests to retrieve document content from arbitrary external endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 02:10 PM
Security Audit — agent-trust-hub — connect-ai-docusign