The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes local shell commands to execute a Python script (openclaw_relay.py) for interacting with the Discord relay. It passes user-provided message content as command-line arguments.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it ingest and processes messages from an external Discord session.
Ingestion points: Output received from the openclaw_relay.py script representing external Discord communications.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the provided markdown.
Capability inventory: Execution of local Python scripts via shell commands.
Sanitization: No evidence of sanitization, escaping, or validation of the ingested content is provided in the skill instructions.

discord-clawd