The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The script scripts/package_skill.py performs file system operations (reading, writing, and zipping) using standard Python libraries like pathlib and zipfile. These operations are local to the user-specified directory and do not involve shell execution of untrusted input.
[REMOTE_CODE_EXECUTION] (SAFE): No remote code execution patterns, external downloads, or network requests were found in any of the scripts.
[DATA_EXFILTRATION] (SAFE): The skill does not access sensitive files (e.g., SSH keys, credentials) or perform network operations. It strictly manages skill metadata and packaging.
[PROMPT_INJECTION] (SAFE): The documentation files (references/output-patterns.md, references/workflows.md) contain instructional templates but do not include patterns designed to bypass AI safety guardrails or override system instructions.
[DYNAMIC_EXECUTION] (SAFE): The scripts/quick_validate.py script uses yaml.safe_load() to parse frontmatter, which is the recommended secure way to handle YAML data.

skill-creator