The Agent Skills Directory

[SAFE]: The skill is a standard text-based roleplay tool that facilitates training scenarios through natural language interaction.
[NO_CODE]: No executable scripts, binaries, or code files are included in the skill; it consists solely of markdown instructions and reference text.
[PROMPT_INJECTION]: The instructions do not contain attempts to bypass AI safety guidelines, reveal system prompts, or override agent constraints.
[DATA_EXFILTRATION]: No sensitive file paths, credential patterns, or network communication tools are utilized.
[EXTERNAL_DOWNLOADS]: The skill does not download external packages or remote scripts.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the execution of remote or dynamically generated code.
[COMMAND_EXECUTION]: No shell commands, subprocess calls, or privilege escalation patterns were detected.

adversarial-roleplay