The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the exec tool to run a CLI utility named betaclaw. User-provided inputs including {GROUP_ID}, {delay}, {message}, and {TASK_ID} are interpolated directly into shell commands. If these inputs are not properly sanitized or quoted by the platform, it could allow for arbitrary command execution.
[INDIRECT_PROMPT_INJECTION]: The skill enables users to schedule content that will be processed by the agent at a later time, creating an attack surface where malicious instructions could be embedded in the scheduled message.
Ingestion points: The {message} parameter within the betaclaw schedule once command in SKILL.md.
Boundary markers: Absent. The message is passed as a string without explicit delimiters or instructions for the agent to ignore embedded commands upon retrieval.
Capability inventory: The skill has access to the exec tool for shell command execution.
Sanitization: None detected. The skill does not define validation or escaping for the user-supplied message content.

schedule