auvik-network-alerts
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script at
mcp-servers/auvik-mcp/auvik_mcp_server.pyto facilitate its core alert-triaging functionality. - [DATA_EXFILTRATION]: The skill connects to well-known Auvik API endpoints (e.g.,
auvikapi.us1.my.auvik.com) to fetch monitoring data, which is consistent with its stated purpose and vendor origin. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes data like alert definitions and device names retrieved from the Auvik API.
- Ingestion points: Data enters the agent's context through the
auvik_list_alertstool during API data retrieval. - Boundary markers: No explicit delimiters or boundary markers are defined for the external data in the instruction file.
- Capability inventory: The skill's capabilities are limited to local Python script execution for processing network data.
- Sanitization: There is no documentation regarding the sanitization or validation of strings returned from the external API.
Audit Metadata