The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves ingesting data from potentially untrusted external sources, such as spreadsheets, legacy system exports, and discovery data.
Ingestion points: The migration methodology relies on reading data from sites.csv, devices.csv, and other external files as described in references/import-patterns.md and references/source-mapping.md.
Boundary markers: The skill lacks explicit instructions for the agent to treat imported data as untrusted or to utilize delimiters/boundary markers when processing spreadsheet content to prevent the execution of embedded instructions.
Capability inventory: The skill exhibits significant write capabilities, utilizing pynetbox and the Diode SDK to perform bulk object creation and modification within the NetBox database (references/import-patterns.md).
Sanitization: The provided Python code patterns perform direct mapping of source fields to API payloads without implementing sanitization or validation checks for malicious content within the data values.

netbox-migration