azure-upgrade
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests potentially untrusted data from existing Azure resource configurations (app settings, connection details, and binding metadata) and interpolates them into reports and status trackers.
- Ingestion points: Data is collected from Azure CLI command outputs (e.g.,
az functionapp config appsettings list) within the automation scripts. - Boundary markers: The skill does not define clear delimiters or use specific instructions to prevent the agent from interpreting ingested configuration values as instructions.
- Capability inventory: The agent has the ability to execute shell commands via the Azure CLI and write files to the workspace.
- Sanitization: No explicit sanitization or validation of external configuration data is performed before it is added to the agent's context.
- [COMMAND_EXECUTION]: The skill relies on executing Azure CLI (
az) commands to perform assessments and migrations. These commands are part of the skill's primary functionality and are designed to be executed within the user's authenticated context.
Audit Metadata