The Agent Skills Directory

[SAFE]: The skill consists of instructional Markdown documentation outlining best practices for software testing. It does not contain any executable scripts, binary files, or network-enabled tools.
[INDIRECT_PROMPT_INJECTION]: The skill instructions create a data ingestion surface by directing the agent to process external requirements and source code. • Ingestion points: Instructions in SKILL.md to read requirements, changed code, and fixtures. • Boundary markers: None identified. • Capability inventory: No scripts or tool definitions are provided within the skill. • Sanitization: Not specified. The risk is evaluated as minimal due to the purely descriptive nature of the skill.

flow-test