The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes JSON metadata from an external source (api.aliyun.com). While this is a well-known service, processing untrusted external content represents a potential indirect injection surface.
Ingestion points: scripts/list_openapi_meta_apis.py fetches product API documentation from https://api.aliyun.com/meta/v1/products/.
Boundary markers: Absent; the external JSON is parsed and its contents are directly used to generate Markdown lists.
Capability inventory: The skill has the capability to write files to the local output/ directory and execute local scripts.
Sanitization: The script uses standard JSON parsing but does not sanitize or validate the content of the API names or documentation strings before writing them to output files.
[EXTERNAL_DOWNLOADS]: The Python script scripts/list_openapi_meta_apis.py performs HTTP GET requests to api.aliyun.com to retrieve OpenAPI metadata. This targets a well-known service and is used for documentation discovery.
[COMMAND_EXECUTION]: The skill executes local Python scripts (scripts/list_openapi_meta_apis.py) and standard tools like py_compile and mkdir for validation and data processing purposes.

aliyun-dlf-manage