azure-functions-diagnostics

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing external telemetry and log data.
  • Ingestion points: Consumes user-provided symptoms, error messages, command outputs, and Azure telemetry (Application Insights/Log Analytics) as defined in SKILL.md and workflow.md.
  • Boundary markers: There are no explicit instructions to use delimiters or delimiters for the ingested log data to separate it from the system prompt.
  • Capability inventory: The workflow in workflow.md indicates the agent may use CLI tools (az, func, azd), clone repositories, and perform deployments or restarts.
  • Sanitization: The skill includes strong mitigation through explicit guardrails in SKILL.md that command the redaction of secrets (SAS URLs, tokens, keys) and require user confirmation for all mutation or disruptive actions.
  • [COMMAND_EXECUTION]: The skill references the use of official Azure management and development tools, including the Azure CLI (az), Azure Developer CLI (azd), and Azure Functions Core Tools (func), for diagnosis and remediation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 02:05 AM
Security Audit — agent-trust-hub — azure-functions-diagnostics