The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user-provided CSV files and incorporates it into generated Markdown reports, which may be subsequently read by the AI agent.
Ingestion points: The scripts/x-analyze.py script reads data from the Post text column of user-supplied account_analytics_content_*.csv files.
Boundary markers: No specific delimiters or 'ignore embedded instructions' warnings are implemented to separate external data from the report structure.
Capability inventory: The skill is capable of reading local files, writing reports to disk, and executing local Python scripts to process data.
Sanitization: The raw content from the CSV's text field is interpolated directly into the final Markdown report without filtering or escaping, allowing for potential malicious instructions to be embedded in the agent's context.
[DYNAMIC_EXECUTION]: The script scripts/x-analyze.py uses subprocess.check_call to automatically install the matplotlib library at runtime if it is not found in the environment.
Evidence: Line 159 in scripts/x-analyze.py attempts to run pip install matplotlib or uv pip install matplotlib using a static command list.
[EXTERNAL_DOWNLOADS]: The skill initiates downloads from the official Python Package Index (PyPI) to satisfy the matplotlib dependency if it is missing.
Context: The download targets a well-known and trusted library registry.

x-analytics