The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to bypass safety filters or override system instructions were detected. The instructions are strictly focused on content generation logic.
[DATA_EXFILTRATION]: No network operations (such as curl or wget) or sensitive file access patterns were found. The skill operates locally on provided content atoms.
[CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or secrets are present in the skill metadata or body.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute external scripts or packages. It relies on internal reference files for platform specifications and formulas.
[COMMAND_EXECUTION]: No shell commands or subprocess executions are invoked. Output is restricted to writing markdown files to a specific directory.
[OBFUSCATION]: The content is written in clear, human-readable markdown without any hidden characters, Base64 encoding, or homoglyph-based evasion techniques.

repurpose-tiktok