prisma-sdwan-status

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill correctly uses environment variables for sensitive API credentials, avoiding hardcoded secrets.\n- [COMMAND_EXECUTION]: The skill executes a Python script to start the MCP server process.\n- [EXTERNAL_DOWNLOADS]: The skill relies on an MCP server implementation from a community developer.\n- [PROMPT_INJECTION]: The skill fetches events and alarms from the Prisma SD-WAN API, presenting a surface for indirect prompt injection.\n
  • Ingestion points: External data is ingested via the get_events and get_alarms tool calls to the Prisma API.\n
  • Boundary markers: No boundary delimiters are utilized to separate untrusted data from the agent instructions.\n
  • Capability inventory: The skill provides read-only monitoring and health-check capabilities.\n
  • Sanitization: There is no description of data filtering or sanitization performed on the API responses.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:29 PM
Security Audit — agent-trust-hub — prisma-sdwan-status