meraki-wireless-ops

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the official CiscoDevNet repository for its Meraki Magic MCP server implementation, which is a recognized and well-known technology provider.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through its ingestion of external Meraki wireless data.\n
  • Ingestion points: Data enters the agent's context through several API methods in SKILL.md, including getWirelessClientConnectivityEvents, getWirelessSSIDs, and getWirelessSignalQuality.\n
  • Boundary markers: The skill does not define specific markers or guardrails to segregate retrieved telemetry data from instructions.\n
  • Capability inventory: The skill includes write-access tools such as updateWirelessSSID and createWirelessRFProfile which could be targetable via poisoned data inputs.\n
  • Sanitization: No explicit sanitization or content validation is specified for the data returned by the Meraki cloud APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 12:31 AM