The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands like terminal-notifier, say, and sleep to provide its functionality. Evidence: The Commands section illustrates the use of backgrounded shell commands with strings passed to the -message flag. Risk: There is a possibility of command injection if user-provided notification messages are not handled securely by the agent.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through user-controlled notification content. Ingestion points: Notification messages provided by users. Boundary markers: None. Capability inventory: Execution of arbitrary shell commands via system subprocesses. Sanitization: The skill instructions do not provide guidance on escaping or validating user-provided strings before they are incorporated into shell commands.

c-timer