The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local script scripts/api-request.sh for all API operations, which is the primary mechanism for its functionality.
[DYNAMIC_EXECUTION]: The skill utilizes eval $(api --env) to load environment variables such as TOKEN and AD_ACCOUNT_ID from the output of an internal helper script, following standard configuration practices for this environment.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from the Spotify Ads API, presenting an attack surface for indirect instructions.
Ingestion points: API response bodies containing change history records (SKILL.md).
Boundary markers: None specified in the display instructions to separate data from instructions.
Capability inventory: The skill has access to Bash, Read, and AskUserQuestion tools (SKILL.md).
Sanitization: The instructions do not define explicit sanitization for API-returned strings like entity names or change values before rendering them to the agent.

change-history