The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes Python scripts (convert_sync_to_async_cm.py, generate_async_context_manager.py, validate_context_managers.py) that perform file operations and code analysis. These scripts use the built-in ast (Abstract Syntax Tree) module to parse and transform code safely without executing it.
[DATA_EXFILTRATION]: No network operations, hardcoded credentials, or access to sensitive system paths (e.g., SSH keys, AWS credentials) were found. The skill only requests access to standard file manipulation tools (Read, Grep, Glob, Write, Edit) necessary for its purpose.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts. All dependencies referenced are either from the Python standard library (contextlib, ast, argparse, pathlib) or well-known development libraries (pytest, neo4j, aiofiles) used in instructional examples.
[PROMPT_INJECTION]: The instructions in SKILL.md are focused on technical implementation and do not contain any instructions that attempt to bypass AI safety filters or override system prompts.
[DYNAMIC_EXECUTION]: While generate_async_context_manager.py assembles code strings using user-provided input for templates, it does not use eval() or exec(). It validates the resulting code string using ast.parse() for syntax correctness before writing it to a file, which is a secure practice for code generation tools.

python-best-practices-async-context-manager