azure-diagnostics

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): In references/azure-resource-graph.md, the skill instructs the agent to run az extension add --name resource-graph. This involves downloading and installing an external extension for the Azure CLI. While this is a standard tool from a trusted organization (Microsoft), it is an external dependency.
  • PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection due to its core function of analyzing external logs.
  • Ingestion points: Application logs via az containerapp logs show and Application Insights telemetry through KQL queries in references/kql-queries.md.
  • Boundary markers: Absent. The skill does not define specific delimiters or instructions to ignore embedded commands within log data.
  • Capability inventory: The skill possesses significant capabilities, including the ability to modify container app configurations (az containerapp update, az containerapp registry set) and trigger automated diagnostics via MCP tools.
  • Sanitization: No sanitization logic is provided to filter malicious instructions that might be present in application exceptions or log traces.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 03:34 AM