The Agent Skills Directory

[Prompt Injection] (SAFE): The skill provides stylistic constraints for writing tasks. There are no attempts to bypass safety filters, extract system prompts, or override core agent instructions beyond the scope of a writing assistant.- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, credential patterns, or network communication code were found.- [Remote Code Execution] (SAFE): The skill does not include any commands for downloading or executing remote scripts (curl, wget, etc.).- [Indirect Prompt Injection] (LOW): The skill is designed to process user-provided text for rewriting. While this is an ingestion surface, the skill lacks the necessary capabilities (file system access, network requests, subprocess execution) to be exploited maliciously. The risk is limited to stylistic influence on the AI's output.- [No Code] (SAFE): The skill contains only markdown instructions and no scripts or configuration files that could execute commands.

ai-tells