bkend-data
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides links to official documentation hosted on the vendor's GitHub repository (ww-w-ai/bkend-docs). These are used as live references for data tools, table management, and database overviews.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data through database queries (backend_data_list, backend_data_get) and documentation fetching (WebFetch). While this creates a surface where the agent might encounter untrusted content from the database or remote files, it is a standard functional requirement for a database management skill and lacks any patterns suggesting malicious intent.
- Ingestion points: Database records fetched via MCP tools; documentation content retrieved via WebFetch.
- Boundary markers: Not explicitly defined in the reference documentation.
- Capability inventory: Includes file system modification (Write, Edit) and command execution (Bash) capabilities.
- Sanitization: Relies on the agent's internal safety guardrails for processing retrieved content.
Audit Metadata