The Agent Skills Directory

[REMOTE_CODE_EXECUTION] (SAFE): The quick_validate.py script uses yaml.safe_load() to parse frontmatter, which correctly prevents the execution of arbitrary Python objects through YAML tags.
[COMMAND_EXECUTION] (SAFE): The package_skill.py and quick_validate.py scripts perform local file operations using standard libraries (pathlib, zipfile, re). No subprocess execution, shell commands, or dynamic code evaluation (eval/exec) were found.
[DATA_EXFILTRATION] (SAFE): No network requests (curl, wget, requests) or patterns indicating data exfiltration were detected. The scripts operate exclusively on local files for the purpose of packaging.
[PROMPT_INJECTION] (SAFE): The documentation files (output-patterns.md, workflows.md) provide structural examples for output and logic flow. They do not contain instructions that attempt to override AI safety constraints or bypass system prompts.
[CREDENTIALS_UNSAFE] (SAFE): No hardcoded API keys, tokens, or sensitive credentials were found in the scripts or documentation.

skill-creator