The Agent Skills Directory

[COMMAND_EXECUTION]: The skill detects and executes shell commands (e.g., npm test, pytest, go test) derived from project configuration files like package.json or pyproject.toml to run tests and check coverage.
[REMOTE_CODE_EXECUTION]: The skill generates new test files and subsequently executes them using the project's detected test runner. This dynamic execution of generated content is a core functionality but poses a risk if the generation process is influenced by malicious source code.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted local data to drive logic and execution.
Ingestion points: The skill reads source code files and project metadata (package.json, configuration files).
Boundary markers: Absent; there are no delimiters or instructions provided to the agent to disregard instructions potentially embedded within the source files being analyzed.
Capability inventory: The skill has the ability to write files to the local system and execute arbitrary shell commands via detected test runners.
Sanitization: Absent; the skill extracts commands from configuration files and executes them without validation.

test-gen