PraisonAIAgents is a multi-agent teams system. The memory hooks executor in PraisonAIAgents passes a user-controlled command string directly to `subprocess.run()` with `shell=True` at `src/praisonai-agents/praisonaiagents/memory/hooks.py`. No sanitization is performed, allowing shell metacharacters to be interpreted by `/bin/sh` before the intended command executes. Two attack surfaces exist: through `pre run command` and `post run command` hook event types registered through the hooks configuration, and through the `.praisonai/hooks.json` lifecycle configuration. An agent gaining file-write access through prompt injection can overwrite `.praisonai/hooks.json` and have its payload execute silently at every subsequent lifecycle event without further user interaction.