ralph-review-deep

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). High-risk: the skill deliberately packages repository contents (including plan/docs and bd outputs) into prompts sent to third‑party LLMs and instructs those LLMs to execute tool calls (bash) locally — creating clear avenues for data exfiltration and remote code execution if the LLMs or opencode tool integration are misused or compromised.