The Agent Skills Directory

[Command Execution]: The skill instructions include running shell commands such as make coverage and uv run coverage report -m to measure and report on test coverage. These are standard operations within a development environment and are consistent with the skill's purpose of coverage measurement and improvement.
[Indirect Prompt Injection Surface]: The skill processes external data from artifacts like .coverage and coverage.xml to identify testing gaps.
Ingestion points: The skill reads .coverage and coverage.xml files in SKILL.md Step 1 and 2.
Boundary markers: No explicit delimiters are specified for these file contents.
Capability inventory: The agent can execute make coverage, uv run, and edit source code (Step 4).
Sanitization: No specific sanitization logic is described for the coverage report content. While ingestion of external files is a potential surface for indirect prompt injection, it is the primary function of the skill and is handled within the context of a structured coverage analysis workflow.

test-coverage-improver