The Agent Skills Directory

[COMMAND_EXECUTION]: The script executes standard system commands including ps, launchctl, find, security, and jq to collect and display status information about the local recording environment.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted data from the local environment.
Ingestion points: Filenames found in /tmp and ~/eon, process arguments from ps aux, and entries from chunker.log.
Boundary markers: None; the output is printed directly to the agent's context without delimiters or instructions to ignore embedded content.
Capability inventory: The skill has access to the Bash tool, allowing for subsequent command execution.
Sanitization: The script does not perform sanitization or validation on the ingested data before presenting it to the agent.

daemon-status