The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from test outputs and configuration files, creating a potential surface for indirect prompt injection if those files contain malicious instructions. * Ingestion points: Reads project files such as package.json and vitest.config.*, and captures stdout/stderr from npx vitest in SKILL.md. * Boundary markers: The instructions require formatting results into a structured report using clear headers and delimiters. * Capability inventory: Employs Bash for command execution and Read for file access. * Sanitization: No specific filtering or sanitization of test failure messages is described before reporting.

vitest-runner