The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The script package_skill.py automates the creation of a ZIP archive from a local directory. It uses standard library functions and does not execute arbitrary shell commands or untrusted binaries.
[DATA_EXFILTRATION] (SAFE): There are no network calls or functions that would facilitate the transmission of data to external endpoints. The file operations are strictly local to the filesystem.
[PROMPT_INJECTION] (SAFE): The documentation files (output-patterns.md and workflows.md) provide structured templates for the agent. These examples do not contain instructions to override system prompts or bypass safety filters.
[DYNAMIC_EXECUTION] (SAFE): The validation logic in quick_validate.py correctly uses yaml.safe_load() for parsing configuration files, which prevents the execution of arbitrary Python objects during the parsing process.

skill-creator