The Agent Skills Directory

[COMMAND_EXECUTION]: The skill contains several Python scripts in the scripts/ directory that use subprocess.call to chain execution between local utility scripts for file conversion and parsing.\n
Evidence: Found in scripts/convert_to_csv.py, scripts/parse_excel.py, scripts/batch_convert_templates.py, and other similar wrapper scripts.\n
Context: These operations are part of the skill's core functionality for managing QA output formats. The scripts use sys.executable and normalized paths, avoiding shell execution and remote code invocation.\n- [PROMPT_INJECTION]: The skill's primary function involves processing external documentation and requirements, which presents a surface for indirect prompt injection.\n
Ingestion points: prompts/api-testing.md instructs the agent to process materials such as OpenAPI/Swagger docs, Postman collections, and WSDL files.\n
Boundary markers: Absent. There are no explicit delimiters or safety instructions provided to the agent to distinguish between user instructions and external data content.\n
Capability inventory: The skill has the capability to read and write files and execute local processing scripts within its directory.\n
Sanitization: Absent. The provided scripts perform format parsing and conversion without explicit sanitization of the input text content.

api-testing