The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes user-provided source files to generate test cases, which introduces an attack surface for indirect prompt injection. If the source files contain adversarial instructions, the agent might inadvertently follow them during the generation process. Ingestion points: source file path in SKILL.md. Boundary markers: absent. Capability inventory: local shell execution via npx vitest. Sanitization: absent.
[COMMAND_EXECUTION]: The skill executes npx vitest to run tests on local files. This is a standard development task but involves executing shell commands targeting user-specified paths.

write-tests