The Agent Skills Directory

[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by ingesting untrusted configuration data from managed network devices via the Auvik API.
Ingestion points: The auvik_list_configurations tool retrieves the full body of device configuration backups.
Boundary markers: Absent. The instructions do not define delimiters or explicit warnings for the agent to ignore instructions embedded within the retrieved configurations.
Capability inventory: The skill accesses sensitive network configuration data, device lifecycle status, and warranty information for report generation and refresh planning.
Sanitization: Absent. There are no defined processes for filtering or sanitizing the retrieved configuration content before it is added to the agent's context.
[CREDENTIALS_UNSAFE]: The skill utilizes environment variables (AUVIK_USERNAME, AUVIK_API_KEY) for API authentication, which is the recommended practice for secure secret management.
[SAFE]: Network communication is targeted at well-known and official Auvik API endpoints.

auvik-lifecycle