The Agent Skills Directory

[SAFE]: The skill documents legitimate development practices including the use of Ruff for linting and formatting, and python-dotenv for local secret management.
[COMMAND_EXECUTION]: The instructions include the use of the --break-system-packages flag with pip install to bypass PEP 668 restrictions on macOS systems managed by Homebrew. While this bypasses a system safeguard designed to protect the OS-managed Python environment from package conflicts, it is presented as a project-specific workflow standard for development workstations and does not involve unauthorized privilege escalation or execution of untrusted remote code.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection via the processing of untrusted project files:
Ingestion points: The agent reads and modifies .py files and .env files during typical usage.
Boundary markers: No specific delimiters or safety warnings for processing external file content are defined in this skill.
Capability inventory: The skill utilizes subprocess execution for pip and ruff commands.
Sanitization: There are no explicit sanitization or filtering steps for data ingested from the project files before it is processed by the agent tools.

python-style