The Agent Skills Directory

[SAFE]: The skill's primary purpose is to provide educational content and code review guidelines for frontend performance optimization. No malicious intent or dangerous patterns were identified.
[EXTERNAL_DOWNLOADS]: The skill references legitimate developer resources, including frontendchecklist.io and the official HTML specification (html.spec.whatwg.org). These are well-known, trusted documentation sites and do not represent a security risk.
[DATA_EXPOSURE]: Analysis of the instructions and scripts shows no access to sensitive system files, environment variables, or credentials. There are no network exfiltration patterns.
[REMOTE_CODE_EXECUTION]: The skill does not attempt to download or execute external scripts or packages. Code examples provided in the reference material are for documentation purposes and are not executed by the skill logic.
[INDIRECT_PROMPT_INJECTION]: The skill processes HTML markup provided by the user to identify lazy-loading improvements. While this represents a data ingestion surface, the skill lacks high-privilege capabilities or autonomous execution tools, and the instructions are focused on providing static code review feedback, resulting in no identifiable risk.

offscreen-lazy