The Agent Skills Directory

[SAFE]: No security issues were detected during the analysis of the skill's core instructions, techniques, or reference files.
[PROMPT_INJECTION]: The skill does not contain instructions that attempt to override agent behavior, bypass safety guidelines, or extract system prompts. All instructions are focused on providing graphics development templates.
[DATA_EXFILTRATION]: No sensitive file access (e.g., .ssh, .env) or network operations to external or untrusted domains were found. All code provided is intended for client-side GPU execution or within sandboxed shader environments.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts from unknown sources. The provided JavaScript and GLSL templates are self-contained and instructional.
[OBFUSCATION]: No obfuscated text, zero-width characters, or homoglyph attacks were identified. Mathematical constants and hex values used in the code (e.g., for hash functions and LCG random generators) are standard in the field of computer graphics.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not utilize the dynamic command execution syntax (!command) to run shell commands at load time.

shader-dev