docusign-automation
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill automates the creation and management of DocuSign envelopes using data provided by users or external sources, creating a vulnerability surface where data could be interpreted as instructions by the agent. * Ingestion points: The skill ingests untrusted data for
templateRoles(names and emails),emailSubject, andemailBlurbvia tools likeDOCUSIGN_CREATE_ENVELOPE_FROM_TEMPLATE. * Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to separate user data from the agent's execution logic. * Capability inventory: The skill has the capability to create, send, and modify legal signature envelopes, as well as list account templates. * Sanitization: No explicit sanitization, validation, or escaping of user-provided strings is mentioned in the workflow instructions.
Audit Metadata