The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructions do not contain any attempts to override safety filters, bypass system constraints, or extract sensitive system prompts. The language is purely instructional and focused on its stated purpose.
[DATA_EXFILTRATION]: No patterns of sensitive file access or unauthorized data transmission were found. The skill uses standard agent tools (WebSearch and WebFetch) to gather public social media trends, which is consistent with its functionality.
[REMOTE_CODE_EXECUTION]: There are no instances of remote script downloads, package installations, or dynamic code execution (eval/exec) within the skill or its references.
[COMMAND_EXECUTION]: The skill does not perform any shell command execution or process spawning. It relies entirely on text generation and provided research tools.
[DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive environment variables are present in the files.
[SAFE]: The skill includes accessibility-focused instructions, such as mandatory PascalCase for hashtags to support screen readers, and respects platform-specific limits to avoid spam-like behavior.

create-hashtags