The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override agent behavior or bypass safety constraints were found. The instructions are focused entirely on technical guidance for three.js.
[DATA_EXFILTRATION]: No sensitive file paths or unauthorized network operations were detected. All external links point to the official threejs.org documentation.
[CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or secrets are present. The skill explicitly advises against hardcoding sensitive information in its 'Gotchas' section.
[REMOTE_CODE_EXECUTION]: The skill does not contain commands to download or execute remote scripts. It provides high-level workflow steps rather than executable code blocks.
[OBFUSCATION]: No encoded content, zero-width characters, or hidden text patterns were identified in the files.
[DYNAMIC_EXECUTION]: There are no uses of eval(), exec(), or other dynamic code generation techniques.

threejs-postprocessing