The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation providing guidelines, prompt patterns, and parameter settings for image editing. No malicious instructions, obfuscation, or data exfiltration patterns were identified.
[COMMAND_EXECUTION]: The documentation provides examples for using a local CLI wrapper (tools/image_edit.py) via uv run. These examples demonstrate standard usage for passing prompts and image paths to an image editing utility and do not include suspicious command chaining, shell injection, or privilege escalation attempts.
[INDIRECT_PROMPT_INJECTION]: The skill documentation includes best practices for constructing prompts to ensure identity preservation and avoid model drift. These guidelines serve as boundary markers and safety measures for image generation tasks rather than introducing vulnerabilities.

qwen-edit