Intent-Code Divergence
Medium
- Confidence
- 78% confidence
- Finding
- The safety section asserts that untagged actions are reads and safe to run directly, but the same document also includes operational commands such as CLI installation and `oo auth login` that are not read-only. This can mislead an agent or user into treating the overall skill workflow as harmless, increasing the chance of executing environment-changing commands without adequate confirmation.
