NYC

appinsights-instrumentation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) due to its data ingestion patterns.
  • Ingestion points: The main skill instructions (SKILL.md) direct the agent to 'Read the source code to make an educated guess' about the programming language and framework.
  • Boundary markers: Absent. There are no instructions to the agent to treat source code as untrusted data or to use specific delimiters.
  • Capability inventory: The skill has the ability to execute Azure CLI commands (az), install system/language packages (npm, pip, dotnet), and modify the user's source code.
  • Sanitization: Absent. No escaping or validation is performed on the content read from the workspace before it influences the agent's decision-making flow.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill references and installs official Microsoft packages (Azure.Monitor.OpenTelemetry.AspNetCore, @azure/monitor-opentelemetry, and azure-monitor-opentelemetry) from trusted registries. These qualify for downgraded severity under [TRUST-SCOPE-RULE].
  • [COMMAND_EXECUTION] (SAFE): The skill utilizes standard Azure CLI (az) commands for resource creation and environment configuration, which are consistent with its stated purpose of cloud infrastructure management.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 09:58 PM