The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions found attempting to override system behavior, bypass safety filters, or extract system prompts. The instructions are focused entirely on formatting tasks.
[Data Exposure & Exfiltration] (SAFE): There are no commands or functions that access sensitive local files or perform network operations. No hardcoded credentials were found.
[Obfuscation] (SAFE): All text is human-readable with no hidden characters, Base64 encoding, or homoglyph-based evasion techniques.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not reference or install any external packages (Python or Node.js) and contains no remote script execution patterns.
[Indirect Prompt Injection] (INFO): The skill is designed to process external content for formatting. While it lacks explicit sanitization or delimiters for this data, it possesses no dangerous capabilities (like shell execution or file writing) that could be exploited through such an injection.
[Dynamic Execution] (SAFE): No use of eval, exec, or runtime compilation of code was detected.

markdown-formatter