The Agent Skills Directory

[NO_CODE]: The skill consists entirely of natural language documentation and instructions. It does not include any scripts, binaries, or automated logic.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external image files, which represents a potential attack surface for instructions embedded within images. * Ingestion points: User-provided images and screenshots (SKILL.md). * Boundary markers: No instructions are provided to the agent to ignore text content within images. * Capability inventory: Image analysis, resolution enhancement, and file creation. * Sanitization: No input validation or sanitization is described.
[SAFE]: No malicious patterns, prompt injections, or unauthorized command executions were detected.

image-enhancer