The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands including grep, find, pytest, and npx vitest to discover project configurations and execute test suites on the local system.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because its workflow involves reading and processing untrusted project files.
Ingestion points: Reads existing test files (Step 2) and target module source code (Step 3) to identify patterns and logic.
Boundary markers: There are no defined boundary markers or instructions to the model to ignore potential instructions embedded within the code comments or strings of the analyzed files.
Capability inventory: The skill possesses the ability to write new files to the filesystem and execute those files using system-level test runners like pytest and vitest via npx.
Sanitization: The workflow does not include a step to sanitize or escape the content of the ingested source files before they are used to prompt the LLM for test generation.

add-tests