The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the agent to execute shell commands using python3 to interact with project-specific scripts like live_device.py and path_claims.py for managing device status and file claims.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests data from project files (Kotlin, Java, Swift) and monitors external outputs from live_device.py and .moru/live-device/events.jsonl to verify build results.
Ingestion points: Project source files and .moru/live-device/events.jsonl.
Boundary markers: No specific delimiters or warnings for embedded instructions are defined for the ingested data.
Capability inventory: The skill utilizes shell command execution (python3) and file system write operations.
Sanitization: No evidence of sanitization or filtering of external content is present in the instructions.

live-device