The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @ably/cli tool using npm install -g @ably/cli. This is a legitimate tool provided by the vendor, Ably.
[COMMAND_EXECUTION]: The skill operates by executing various CLI commands (ably subscribe, ably publish, ably auth) to interact with the Ably platform for diagnostic purposes.
[INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest and analyze live message traffic and logs from external Ably channels, which represents a surface for indirect prompt injection if the data contains malicious instructions.
Ingestion points: Commands such as ably subscribe, ably presence, and ably logs in SKILL.md bring external realtime data into the agent's context.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are provided to the agent for this data stream.
Capability inventory: The skill provides significant management capabilities, including the ability to publish messages, modify channel rules, and manage API keys or tokens.
Sanitization: The instructions do not include any steps to sanitize or validate the content of the realtime data before the agent processes it.

debugging-with-ably-cli