The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructions focus exclusively on content formatting and tone adaptation. No patterns involving system prompt extraction, safety filter bypass, or role-play jailbreaks were identified.
[DATA_EXFILTRATION]: No network operations, hardcoded credentials, or access to sensitive local file paths (such as .ssh or .env) were detected. The skill writes generated content to a defined local directory (snapchat/).
[REMOTE_CODE_EXECUTION]: The skill does not perform any external downloads or execute remote scripts. It relies on local reference files for platform specifications and voice guidelines.
[COMMAND_EXECUTION]: There are no shell command executions, subprocess spawns, or use of dynamic context injection (!command) patterns.
[OBFUSCATION]: The file contains clear, human-readable markdown and YAML. No Base64, zero-width characters, homoglyphs, or other encoding techniques were used to hide content.
[SAFE]: The skill adheres to its stated purpose of repurposing content for social media. All logic is transparent, and input/output flows are standard for content generation tasks.

repurpose-snapchat