The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's logic relies on the execution of local shell scripts, specifically scripts/api-request.sh and scripts/fetch-openapi-schema.sh, which are used for API communication and schema retrieval.
[DYNAMIC_EXECUTION]: The agent is instructed to use eval on the output of a local script (api --env) to load environment variables. This represents a dynamic execution pattern where shell commands are generated and executed at runtime.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it fetches and follows instructions from external documents provided by the Spotify Ads API at runtime.
Ingestion points: The agent retrieves the public OpenAPI document and the Ad Product Catalog via API calls.
Boundary markers: The instructions do not specify the use of delimiters or safety warnings for these external inputs, directing the agent to use them as the source of truth for operation parameters.
Capability inventory: The skill can execute shell scripts and API requests, providing a path for ingested data to influence tool usage.
Sanitization: There is no evidence of content sanitization or integrity verification for the fetched documents before they are processed by the agent.

spotify-ads-api-reference