The Agent Skills Directory

[COMMAND_EXECUTION]: The skill documentation includes CLI commands using openclaw voicecall, which is the intended mechanism for interacting with the voice plugin.
[PROMPT_INJECTION]: Identified an indirect prompt injection surface because the tool accepts arbitrary string input for the voice message. This is a functional requirement of the skill.
Ingestion points: The message parameter in initiate_call, continue_call, and speak_to_user.
Boundary markers: No explicit markers or instructions to ignore embedded commands are present in the documentation.
Capability inventory: The skill allows for automated voice calls and message delivery via external telephony providers.
Sanitization: The skill does not define specific sanitization or validation logic for the message content.

voice-call