The Agent Skills Directory

[SAFE]: The skill performs legitimate image processing tasks using the Pillow library. It provides scripts for generating favicons (generate_favicons.py) and social media images (generate_og_images.py) based on user-provided images or text.
[EXTERNAL_DOWNLOADS]: The skill identifies and checks for necessary third-party dependencies (Pillow, pilmoji, emoji). These are well-known, standard packages from the official Python Package Index (PyPI). The instructions specify compatible versions (e.g., emoji<2.0.0) to ensure stability.
[COMMAND_EXECUTION]: The skill executes local Python scripts using standard CLI arguments handled by argparse. No arbitrary shell execution or unsafe command construction from untrusted input was detected.
[DATA_EXFILTRATION]: No network operations or unauthorized data transmission patterns were found. The skill operates locally on user-provided files and outputs results to specified local directories.
[PROMPT_INJECTION]: The instructions in SKILL.md are descriptive and provide clear guidance to the agent for interacting with the user. There are no attempts to bypass safety filters or override system-level instructions.
[DATA_EXPOSURE]: The skill includes a validation module (validators.py) that performs safety and quality checks, such as verifying WCAG contrast ratios for generated text-based images and ensuring file sizes meet platform-specific requirements (e.g., Facebook, Twitter).

web-asset-generator