ralph-wiggum-loop
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script 'ralph-loop-example.py' automates the development lifecycle by invoking the 'opencode' agent framework and 'git' CLI. These operations are performed using the 'subprocess' module with argument lists, which is a secure method that prevents shell command injection.\n- [PROMPT_INJECTION]: The skill's primary function involves reading task definitions from 'TODO.md' and agent instructions from 'PROMPT.md' files. This architecture presents a surface for indirect prompt injection if an attacker can modify these local files; however, this is a known risk inherent to agentic development workflows, and the skill provides explicit safety guidance including iteration caps, sandboxing, and manual approval gates.
Audit Metadata