skills/jeremylongshore/claude-code-plugins-plus-skills/documenso-reference-architecture/Gen Agent Trust Hub
documenso-reference-architecture
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate architectural guidance and boilerplate code for professional software development without any detected malicious patterns.\n- [COMMAND_EXECUTION]: The skill includes a shell script
scripts/setup-documenso-structure.shused for initializing the project's directory hierarchy with standardmkdirandtouchcommands.\n- [EXTERNAL_DOWNLOADS]: The documentation and code examples reference official, well-known packages including@documenso/sdk-typescriptandzod.\n- [PROMPT_INJECTION]: The architecture identifies points where external data is ingested (e.g., via webhooks) and follows best practices for mitigation. \n - Ingestion points: Webhook handlers in
src/api/signing/webhook.tsand service inputs.\n - Boundary markers: Present, utilizing Zod schemas to define expected data structures.\n
- Capability inventory: The skill utilizes SDK calls for document creation, status retrieval, and distribution.\n
- Sanitization: Present, using
zodfor strict schema validation and configuration parsing.
Audit Metadata