The Agent Skills Directory

[SAFE]: No malicious patterns or security risks detected during the analysis of the skill's instructions and associated scripts.
[EXTERNAL_DOWNLOADS]: The skill interacts with the official Google Gemini API at generativelanguage.googleapis.com for image generation, file uploads, and search grounding. These are well-known and trusted services provided by Google.
[INDIRECT_PROMPT_INJECTION]: The skill has the attack surface for indirect prompt injection as it ingests untrusted external data from user-provided reference files (images, PDFs, videos) and live web/image search results. However, the instructions explicitly command the agent to treat this content as data only and never as instructions, which follows security best practices for LLM agent development.
[COMMAND_EXECUTION]: The skill utilizes common command-line tools like python3 and magick (ImageMagick) for its core functionality and post-processing. All provided command templates are standard for image processing tasks and do not exhibit malicious intent.

nanobanana