The Agent Skills Directory

[DYNAMIC_EXECUTION]: The Python script scripts/plot_workflow.py dynamically modifies the system search path using sys.path.insert(0, ...) to import modules from ../../text-splitter/scripts and ../../text-truncator/scripts. This creates a dependency on external code residing outside the skill's own directory structure.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill ingests untrusted "story text or story outline" from users to perform plot analysis and expansion (seen in SKILL.md and scripts/plot_workflow.py).
Boundary markers: The workflow instructions do not define clear boundary markers or provide explicit "ignore embedded instructions" warnings when processing the story text.
Capability inventory: The skill orchestrates a chain of sub-tools (text-truncator, text-splitter, plot-keypoints, detailed-plot-analyzer, output-formatter), creating an execution pipeline that could be influenced by malicious content in the input text.
Sanitization: No sanitization or validation logic is present in the provided script to filter potentially harmful instructions within the story input.

plot-workflow