The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes Python scripts (test_suite_generator.py, coverage_analyzer.py, e2e_test_scaffolder.py) that perform file system operations, including reading project source code and writing new test files to the user's workspace.- [EXTERNAL_DOWNLOADS]: The documentation references and integrates with well-known and trusted testing services and frameworks, including Playwright (Microsoft), Jest, and Codecov.- [PROMPT_INJECTION]: The skill processes external, potentially untrusted data by scanning source code files to generate test cases. This creates an indirect prompt injection surface where malicious instructions embedded in comments or code could influence the agent's behavior during the generation process. Ingestion points: Source code files read by generation scripts. Boundary markers: None specified in the scripts. Capability inventory: File read/write access to the project directory. Sanitization: No explicit sanitization of input code content is performed by the utility scripts.

senior-qa