skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/n8n-daily-report/Gen Agent Trust Hub
n8n-daily-report
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by processing external data.
- Ingestion points: The skill reads data from CSV, Excel, and JSON files as described in instructions.md and SKILL.md.
- Boundary markers: Instructions contain a directive to only use user-provided data, which acts as a basic boundary.
- Capability inventory: The skill has network access through n8n HTTP nodes and Python's requests library, and can upload documents to Microsoft SharePoint.
- Sanitization: No specific sanitization or validation logic is implemented for the data processed from external files.
- [EXTERNAL_DOWNLOADS]: The skill makes requests to and interacts with well-known technology services.
- The n8n workflow fetches weather data from OpenWeatherMap and project images from Procore.
- Reports are distributed via Microsoft SharePoint and email.
- These operations use standard APIs from established providers and align with the skill's primary business case.
Audit Metadata