The Agent Skills Directory

[SAFE]: The skill instructions and associated reference documentation focus exclusively on frontend performance optimization and browser lifecycle management. It provides legitimate guidance on replacing the deprecated unload event with modern pagehide and pageshow handlers to enable browser back/forward cache eligibility.
[SAFE]: The code examples demonstrate standard web development patterns, such as using navigator.sendBeacon for analytics and handling state persistence during navigation. No sensitive data access, credential exposure, or unauthorized network operations were found.
[INDIRECT_PROMPT_INJECTION]: The skill functions as a code review tool, which involves ingesting and analyzing untrusted external codebases. This creates a surface for indirect prompt injection if the analyzed code contains adversarial instructions intended to influence the agent's behavior. However, the skill lacks autonomous execution capabilities or high-privilege tools that could be leveraged for an attack, making this a minimal risk inherent to the task of code analysis.

back-forward-cache