The Agent Skills Directory

[SAFE]: The skill serves as an instructional document for quality assurance workflows. It defines a systematic approach to benchmarking skill performance using a scoring rubric and does not contain any executable scripts, binary files, or network-active commands.
[PROMPT_INJECTION]: The skill naturally presents a surface for indirect prompt injection as it is designed to ingest and execute prompts from external tests/test-cases.yaml files. Ingestion point: tests/test-cases.yaml. Boundary markers: Absent. Capability inventory: Executes prompts within the agent environment. Sanitization: Absent, though the skill provides an explicit warning to users to exclude sensitive information from test prompts. As this is the primary intended function of a testing tool, it is categorized as safe behavior.

skill-tester