The Agent Skills Directory

[Prompt-Only Architecture] (SAFE): The skill consists entirely of natural language instructions for the AI agent. There are no associated scripts, executables, or configuration files that could perform unauthorized actions.
[Indirect Prompt Injection Surface] (LOW): The skill accepts external data through variables like $ARGUMENTS and $PROJECT_NAME. While an attacker could embed malicious instructions in the code being documented, the skill lacks the capabilities (such as file writing, command execution, or network access) to execute those instructions. The risk is confined to the quality of the generated text output.

doc-gen