The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions include a Python script utilizing the openpyxl library to read and process the contents of user-provided .xlsx files.
[EXTERNAL_DOWNLOADS]: The setup documentation refers to downloading the skill configuration from the author's GitHub repository (github.com/leenbj/...). These resources are managed by the skill's developer.
[PROMPT_INJECTION]: The skill processes untrusted data from external spreadsheets, which creates a surface for indirect prompt injection attacks.
Ingestion points: Data is read from the 'Company Name' and 'Domain' columns of an external Excel file as specified in SKILL.md.
Boundary markers: The instructions do not define clear delimiters or include warnings to ignore instructions that might be embedded within the input data.
Capability inventory: The skill environment allows for Python script execution, web search tool usage, and file writing to the local system.
Sanitization: The skill lacks logic to sanitize or validate the content of the spreadsheet before using it to drive searches or generate news articles.

chinese-domain-news