The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a Python script scripts/wx_article_stats.py used to process Excel files containing article performance data. The script uses the xlrd library to extract metrics such as read counts, sharing rates, and follower growth.
[DATA_EXPOSURE]: The instructions reference a data file located outside the immediate skill directory at ../title-generator/references/title-data.md, which is used to reuse historical article data.
[EXTERNAL_DOWNLOADS]: The Python utility script relies on the xlrd library, which is a common and well-known dependency for handling legacy Excel file formats.
[INDIRECT_PROMPT_INJECTION]: The skill processes external information from tool watchlists, peer accounts, and statistical spreadsheets, creating a potential surface for indirect prompt injection.
Ingestion points: Tool discovery lists (references/tool-watchlist.md), shared historical data (../title-generator/references/title-data.md), and article statistics in Excel format.
Boundary markers: The skill instructions do not specify any delimiters or safety markers to isolate external data from the agent's core instructions.
Capability inventory: The skill utilizes file system read access and the ability to execute the local Python script scripts/wx_article_stats.py.
Sanitization: There is no evidence of input validation or content sanitization for the data being processed.

topic-research