The Agent Skills Directory

[DYNAMIC_EXECUTION]: The script scripts/plot_workflow.py dynamically modifies sys.path using sys.path.insert to load the text_splitter and text_truncator modules from computed relative paths (../../text-splitter/scripts and ../../text-truncator/scripts). Loading code from outside the skill's root directory via relative paths is a form of dynamic loading from computed paths.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided story text, which presents an attack surface for indirect prompt injection.
Ingestion points: The input_text parameter in the execute_workflow method of scripts/plot_workflow.py.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the script or instructions.
Capability inventory: The skill metadata in SKILL.md specifies access to the Read and Write tools.
Sanitization: The script performs basic validation for non-empty input but does not implement filtering or sanitization of the story content itself.

plot-workflow