The Agent Skills Directory

[NO_CODE]: The skill package does not contain any executable scripts, binaries, or code files. It consists solely of Markdown documentation and natural language instructions for the AI agent.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and process user-provided images, which introduces a potential attack surface for indirect prompt injection if malicious instructions are embedded within the image data.\n
Ingestion points: The skill instructions in SKILL.md define prompts for processing external image files (e.g., screenshot.png).\n
Boundary markers: No explicit delimiters or instructions to ignore embedded textual content within images are provided.\n
Capability inventory: The skill examples imply file system write access for saving enhanced versions of images.\n
Sanitization: No content validation or sanitization mechanisms for the processed images are defined.\n- [EXTERNAL_DOWNLOADS]: The documentation contains links to various external resources, including official repositories and tools from well-known technology organizations and community contributors.\n
The README.md references official repositories from organizations like Anthropic and established developer services like Composio.\n
These references are informational and consistent with the skill's purpose as a curated directory.

image-enhancer