The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts (retention_decomposition_analyzer.py, customer_segmentation_designer.py, cs_coverage_calculator.py) using relative paths to process data files.
[PROMPT_INJECTION]: The skill ingests untrusted data from external files, presenting a potential surface for indirect prompt injection. 1. Ingestion points: The skill reads data from cohorts.json, customers.json, and book.json via analysis scripts. 2. Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the JSON files are provided. 3. Capability inventory: The skill has shell execution capabilities to run Python scripts for data processing. 4. Sanitization: No data validation or sanitization steps are documented for the ingested files.

cco-review