documenso-core-workflow-a
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references documentation and source code from Documenso's official GitHub repositories and developer site.
- [DATA_EXFILTRATION]: The skill performs authorized network operations to the official Documenso API domain (
app.documenso.com) to manage document workflows. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data such as document titles, recipient names, and email addresses to construct API requests. While this is a standard attack surface, it is consistent with the primary purpose of a document management skill.
- Ingestion points: Input parameters for creating documents and adding recipients in both
SKILL.mdandreferences/implementation-guide.md. - Boundary markers: None present in the prompt instructions to delimit untrusted data.
- Capability inventory: File system access to read PDF files and network access to the Documenso API.
- Sanitization: The provided code examples do not include explicit sanitization of the input strings before they are used in API requests.
Audit Metadata