The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill guides the user to install azure-appconfiguration and azure-identity. These are official Microsoft libraries, which are considered trusted sources according to the established safety rules.
[CREDENTIALS_UNSAFE]: The skill documentation describes authentication methods using environment variables for connection strings and endpoints. It uses safe placeholders like Secret=... and <name> for sensitive information, preventing hardcoded credential exposure.
[PROMPT_INJECTION]: The skill involves reading external data from Azure App Configuration, which constitutes an indirect prompt injection surface. Ingestion points: get_configuration_setting and list_configuration_settings methods used in SKILL.md. Boundary markers: None are explicitly defined in the provided code snippets to distinguish retrieved configuration from instructions. Capability inventory: The skill facilitates network operations for reading and writing Azure configuration; no local command execution or file-write capabilities are included in the skill content itself. Sanitization: No specific sanitization or validation of the retrieved configuration values is shown in the provided examples.

azure-appconfiguration-py