The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using the uv package manager to run ruff, pyright, and pytest on a user-specified directory path. This is the primary function of the skill.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted source code from external directories.
Ingestion points: Reads content from all .py files within a user-provided directory path.
Boundary markers: Absent; there are no delimiters or instructions to the agent to ignore embedded instructions within the code files.
Capability inventory: Executes subprocesses (ruff, pyright, pytest) and reads file content to generate reports.
Sanitization: Absent; the skill does not sanitize or validate the content of the files before the agent processes the tool outputs and manual checklist.

code-quality