The Agent Skills Directory

[SAFE]: The skill is a meta-utility for skill development and contains no malicious patterns.
[COMMAND_EXECUTION]: The provided Python scripts (init_skill.py, package_skill.py, quick_validate.py) perform standard file and directory operations (creating directories, writing templates, zipping files). These actions are consistent with the skill's primary purpose and do not involve executing untrusted input or shell commands.
[DATA_EXPOSURE]: No hardcoded credentials, sensitive file path access, or network exfiltration patterns were detected in the scripts or documentation.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute code from external or untrusted sources. All logic is contained within the local scripts.
[PROMPT_INJECTION]: The instructions in SKILL.md and references/ provide procedural guidance for the agent to create high-quality output. There are no attempts to bypass safety filters or override system instructions.
[SAFE]: The quick_validate.py script uses yaml.safe_load() for parsing frontmatter, which is the recommended practice to prevent unsafe deserialization vulnerabilities.

skill-creator