The Agent Skills Directory

[Data Exposure & Exfiltration] (SAFE): The utility script scripts/bump_version.py reads from and writes to specific project files such as pyproject.toml, CHANGELOG.md, and __init__.py. These operations are limited to the current project directory and are consistent with the skill's purpose. No credentials or sensitive system paths are accessed.
[Remote Code Execution] (SAFE): No external downloads or execution of untrusted code were identified. The script uses strictly built-in Python modules (argparse, re, sys, pathlib).
[Prompt Injection] (SAFE): The content in SKILL.md consists of technical instructions and documentation. No prompt injection patterns or attempts to override agent behavior were found.
[Command Execution] (SAFE): There are no subprocess calls or shell commands executed by the provided code. All file manipulations are performed using standard Python I/O.

managing-python-releases