The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses standard instructional language to define its persona and processes. No attempts to bypass safety filters, override system prompts, or implement jailbreak patterns were detected.
[DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive file paths are present. The code snippets provided are generic React/Tailwind templates using placeholders for content.
[REMOTE_CODE_EXECUTION]: There are no commands for downloading or executing external scripts, and no use of package managers like npm or pip.
[COMMAND_EXECUTION]: The skill does not invoke any shell commands or subprocesses. It purely generates text and code templates for the user.
[OBFUSCATION]: No hidden content, encoded strings (Base64/Hex), zero-width characters, or homoglyphs were found. The instructions and code are in clear, plain text.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests a user-provided "brief" to generate copy, it lacks the capabilities (like network access or file writing) to be exploited. It operates as a template-based text generator with no access to external untrusted sources.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not use the !command syntax or any other dynamic loading mechanisms that execute at skill load time.

write-landing