The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill uses eval $(api --env) to dynamically assign environment variables, such as tokens and account IDs, based on the output of the local api-request.sh script.
[DYNAMIC_EXECUTION]: The agent is instructed to load and adhere to logic defined in external markdown reference files, such as live-openapi.md and ad-product-validation.md, at runtime.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external Spotify Ads API responses, creating an attack surface for indirect prompt injection.
Ingestion points: API responses from endpoints like ad_sets list and targets/geos (SKILL.md), as well as content from reference files.
Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands when processing API data.
Capability inventory: The skill has access to the Bash tool for command execution and Read for file access.
Sanitization: There is no evidence of sanitization or filtering applied to external API content before it is processed by the agent.
[COMMAND_EXECUTION]: The skill relies on the Bash tool to execute the api-request.sh wrapper and perform environment configuration.

ads