The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety guardrails, or extract system prompts were detected in the skill instructions or documentation.- [DATA_EXFILTRATION]: The skill does not contain any commands to access sensitive file paths (e.g., SSH keys, credentials) or perform unauthorized network requests. All texture sampling identifiers (e.g., iChannel0) are standard GLSL uniforms used locally within rendering contexts.- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download and execution of remote scripts (e.g., curl|bash) or the installation of unverified external packages.- [EXTERNAL_DOWNLOADS]: The skill's references are strictly limited to internal documentation and local assets. No external URLs or third-party dependencies are leveraged.- [COMMAND_EXECUTION]: No dangerous shell commands, privilege escalation attempts (e.g., sudo), or persistent mechanisms (e.g., crontab) are included. The code provided consists of static GLSL and HTML/JavaScript templates for client-side rendering.- [SAFE]: The skill follows professional development standards for computer graphics, providing accurate mathematical formulas and best practices for WebGL2 adaptation without introducing security vulnerabilities.

shader-dev