The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes project-specific documentation to generate test cases, which introduces a vulnerability surface where malicious instructions embedded in requirement files could influence agent behavior.
Ingestion points: The workflow involves reading test-case/plan.md, clarified-requirements/index.md, and CLAUDE.md to extract test scenarios.
Boundary markers: Prompt templates in references/PROMPTS.md lack explicit delimiters or instructions to prevent the agent from obeying commands embedded within the ingested requirements.
Capability inventory: The skill utilizes Read, Write, and Bash tools to modify files and execute local scripts.
Sanitization: There is no evidence of sanitization or filtering applied to external content before it is interpolated into the generation prompts.
[COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts using the Bash tool for the purpose of validating output formats and exporting data.
Evidence: SKILL.md specifies the use of uv run to execute scripts/validate.py and scripts/to_excel.py during the quality assurance phase.
Purpose: These execution patterns are transparently documented as part of the core testing and reporting workflow.

testcase-generator