The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill describes patterns for ingesting and processing data from external NetBox REST and GraphQL API endpoints.
Ingestion points: Data enters the agent's context through API responses fetched in scripts using requests, httpx, or the pynetbox SDK as described in SKILL.md, rest-api-patterns.md, and graphql-patterns.md.
Boundary markers: No specific delimiters or warnings for the agent to ignore embedded instructions in the fetched data are provided in the implementation examples.
Capability inventory: The skill utilizes network operations (REST, GraphQL, gRPC), credential provisioning via the /api/users/tokens/provision/ endpoint, and file system interactions (e.g., in diode-integration.md for dry-run output).
Sanitization: No explicit sanitization or filtering of API content for prompt injection characters is documented in the code snippets.
[SAFE]: The skill references official vendor SDKs and tools including netboxlabs-diode-sdk, netbox-graphql-query-optimizer, and the pynetbox community library.
[SAFE]: The documentation explicitly promotes security best practices, such as never storing tokens in code and using environment variables for credential management.

netbox-api-integration