The Agent Skills Directory

[Remote Code Execution] (SAFE): No patterns for remote code or external script execution were detected across any of the files.- [Data Exposure] (SAFE): No hardcoded credentials, API keys, or access to sensitive system file paths were identified.- [Prompt Injection] (SAFE): The instructions do not contain malicious bypass markers or attempts to override system safety protocols.- [Indirect Prompt Injection] (LOW): The skill possesses a surface for indirect injection as it ingests user-provided product descriptions to generate scripts. However, it lacks exploitable capabilities (such as file-system access or network requests), limiting the risk to the content of the reasoning output only.- [Command Execution] (SAFE): No use of subprocess, shell commands, or OS-level operations was found in the provided files.

explainer-videos