The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's Python helper package (senpi_runtime_helpers) utilizes the subprocess module to manage the lifecycle of trading daemons. Specifically, it calls pgrep for process discovery in cli.py and uses subprocess.Popen in manage.py to relaunch daemons based on execution arguments stored in local boot.json files. These actions are standard for a process management utility and are consistent with the skill's primary purpose.
[PROMPT_INJECTION]: The skill architecture involves interpolating external signal data (e.g., market breakouts) into LLM prompts for trade decision-making. The provided examples in momentum-guarded-strategy.md show signal ingestion into templates using {{signal_external_momentum}} without strict boundary markers or explicit instructions for the AI to ignore embedded commands. This represents a potential surface for indirect prompt injection from untrusted external data sources, though the severity is low due to the operational context.

senpi-trading-runtime