The Agent Skills Directory

Command Execution Considerations: The skill utilizes shell commands to run pytest, ruff, and a bundled lint_check.py script. This is standard functionality for automated code validation within a development environment.\n- Indirect Prompt Injection Surface: The skill analyzes external source code files. This creates a potential ingestion point where instructions embedded in code could influence the agent's behavior. Ingestion points: File reading described in SKILL.md. Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard embedded commands. Capability inventory: Local command execution via the execute tool. Sanitization: No filtering or escaping is applied to the reviewed code. This is an inherent consideration for skills that process and analyze external source files.

code-review