The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to execute shell commands for linting, formatting, and testing using the uv runtime (e.g., uv run ruff, uv run pytest). It also references the execution of local repository scripts such as scripts/resolve_style_guides.py and scripts/validate_trigger_matrix_sync.py for automation processes.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local source code and configuration files which constitutes an indirect prompt injection attack surface.\n
Ingestion points: Python source files (.py), project configuration (pyproject.toml), and dependency locks (uv.lock) as identified in the SKILL.md and references/trigger-matrix.md.\n
Boundary markers: Absent; the instructions do not provide explicit delimiters or warnings for the agent to ignore instructions embedded within the code being analyzed.\n
Capability inventory: The skill enables the execution of test suites (pytest) and various linters via the shell, which could lead to arbitrary code execution if the ingested files contain malicious code.\n
Sanitization: Absent; the skill lacks directives for the agent to sanitize or validate the integrity of the code before processing or executing it.

python-style-guide